Senior Consultant, AI Transformation Engineer
for headings: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We need to map content.
We have description: "This is a hybrid role About Infinitive ..." The "About Infinitive" is company description. Could be "About the role"? Actually "About Infinitive" is company overview. Could be placed under "About the role"? The instruction: use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can have "About the role" heading and include description of role and company? Probably include company overview under About the role.
Then "What You Will Do:" list of duties: bullet points. Those are responsibilities. So we can have Responsibilities
with - items.
Then "Preferred Experience" and "Qualifications" sections. Preferred Experience could be under Requirements? Or Skills? The headings list includes Requirements, Qualifications, Skills. We need to decide mapping.
We have "Preferred Experience" bullet list of backgrounds and experience with several items. That could be under Requirements or Qualifications. Also there is a "Qualifications" section with bullet list of skills.
Thus we can have:
Requirements
with Preferred Experience content.
Qualifications
with the Qualifications bullet list.
Skills maybe not separate; we could omit if no distinct skills section beyond qualifications.
Pay: we have compensation range: $90,000 - $154,000.00 (note typo double zero). We'll include Pay section.
Schedule: not mentioned; hybrid role indicates hybrid work but not schedule specifics. Should we include Schedule? The rule: only include section if posting has real, specific content. Hybrid role indicates hybrid work arrangement but not schedule like full-time/part-time. Might be considered schedule? Probably not enough detail; we can omit Schedule.
Benefits: not mentioned; omit.
Thus sections: About the role, Responsibilities, Requirements, Qualifications, Pay.
We need to preserve all substantive information, not invent or summarize away detail. Must not include boilerplate like EEO etc. Remove that.
We need to include the company description under About the role. Also mention hybrid role.
Let's extract content:
About Infinitive paragraph: "Infinitive is a data and AI consultancy that helps clients modernize, monetize, and operationalize their data to generate lasting value. They pride themselves on their deep industry and technology expertise, ensuring that they drive and sustain the adoption of new capabilities. Infinitive is committed to aligning their team with their clients' culture, ensuring a successful partnership by bringing the right mix of talent and skills for high return on investment. Infinitive has earned recognition as one of the "Best Small Firms to Work For" by Consulting Magazine, receiving this accolade nine times, most recently in 2026. They have also been honored as a “Top Workplace” by the Washington Post, “Best Places to Work” by the Washington Business Journal, and “Best Places to Work” by Virginia Business."
Also first line: "This is a hybrid role". Could include that.
Thus About the role: combine hybrid role statement and company overview.
Responsibilities: list from "What You Will Do:" with subheadings? The content includes multiple sub-sections: Business Process Transformation, Prompt and Context Engineering, MCP Tools and Handler Engineering, Markdown and Knowledge Architecture, AI Agents and Workflow Engineering, AI Evaluation and Quality, Critical Thinking Is the Core Capability (maybe part of responsibilities). Also includes "Example Engagement", "What Success Looks Like". Those are also responsibilities/outcomes.
We need to preserve all substantive information; we can turn each bullet into - . However the content is paragraph style with colon headings. We could treat each heading as a
- with subtext? Better to keep as
- with the heading bold? But we cannot add extra tags beyond
- and
. We can embed inside - ? Not prohibited but maybe safer to keep plain text. We'll produce
- items each starting with the heading.
Thus we need to split the responsibilities into items:
- Business Process Transformation Lead discovery with executives, business teams, subject matter experts, analysts, and engineers. Decompose complex processes into steps, decisions, inputs, outputs, rules, dependencies, and exceptions. Identify bottlenecks, repetitive work, knowledge gaps, and inefficient handoffs. Challenge legacy process assumptions and design future state workflows around AI enabled capabilities. Create practical roadmaps that connect prototypes to scalable operating models.
- Prompt and Context Engineering Design system prompts, task prompts, reusable instructions, and multi step prompt workflows. Translate requirements, policies, and expert knowledge into explicit instructions, constraints, examples, and escalation conditions. Define structured output formats that people and downstream systems can consume reliably. Determine what context should be persistent, retrieved dynamically, or supplied by the user. Optimize model context for quality, speed, cost, and maintainability.
- MCP Tools and Handler Engineering Design MCP servers, clients, and reusable tools where they improve access to enterprise capabilities. Create clear tool descriptions, efficient parameters, structured responses, and predictable handler behavior. Connect AI applications with APIs, databases, applications, knowledge repositories, and data platforms. Plan permissions, authentication, governance, logging, error handling, and recovery. Define when AI may act, when it should recommend, and when a human must approve.
- Markdown and Knowledge Architecture Create AGENTS.md, CLAUDE.md, README.md, business rules, prompt libraries, process definitions, data dictionaries, tool documentation, architecture notes, and evaluation cases. Organize large amounts of information so both humans and AI can navigate it efficiently. Use hierarchy, references, examples, rules, and exceptions to create durable and reusable context. Manage cross document relationships and reduce unnecessary token consumption.
- AI Agents and Workflow Engineering Design agentic workflows that can plan, retrieve, reason, call tools, and request input. Define authorization boundaries, memory and state, failure recovery, escalation, and human checkpoints. Develop reusable components that support multiple use cases. Use modern AI tools to prototype, document, test, troubleshoot, and accelerate implementation.
- AI Evaluation and Quality Define measurable acceptance criteria and representative evaluation datasets. Test accuracy, consistency, unsupported claims, latency, token use, and cost. Compare models, prompting strategies, tool designs, and workflow alternatives. Analyze failures across the model, prompt, context, data, tool, workflow, and process layers. Build feedback loops that improve the solution over time.
- Critical Thinking Is the Core Capability AI models and tools will continue to change. The enduring capability for this role is the ability to structure difficult problems, test assumptions, and select the simplest reliable approach. Strong candidates naturally ask questions such as: What outcome are we actually trying to achieve? Why does this process exist and which steps create value? What information is required and is it trustworthy? Which decisions are deterministic and which require judgment? What assumptions are we making? How should the system behave when evidence is incomplete or contradictory? What actions can AI safely perform? What is the simplest architecture capable of producing the required outcome?
- Example Engagement A team spends hours reviewing customer requests, policies, transaction data, and historical cases before making a recommendation. The AI Transformation Engineer redesigns the process, defines the data and tools required, creates prompts and durable Markdown instructions, and establishes validation and human decision points. Request → Gather Context → Retrieve Data → Apply Rules → Analyze → Recommend → Human Review → Execute → Learn
- What Success Looks Like Success is measured by better business and engineering outcomes, not by the number of prompts, models, or prototypes produced. Expected results may include: Faster and more reliable business processes Reduced manual work and process complexity More consistent analysis and decisions Faster delivery of AI enabled products and services Better employee and customer experiences Improved data utilization and knowledge access Lower operating cost with appropriate controls Organizations operating differently because of AI
We need to keep all that.
Now Requirements: Preferred Experience bullet list:
"Strong candidates may come from consulting, business analysis, process engineering, product management, solution architecture, software engineering, data engineering, automation, or operations. Experience with several of the following is preferred: Large Language Models, agents, and AI assisted development Prompt engineering and context engineering MCP servers, clients, tools, and handlers Function calling, APIs, and integration design RAG, vector search, and semantic retrieval Python, SQL, JSON, YAML, Markdown, and Git Databricks, cloud, or enterprise data platforms Business transformation, consulting, architecture, process, product, data, or software engineering"
We can make each bullet maybe separate lines but it's okay as one
- with the whole text.
Qualifications bullet list:
"Strong analytical and critical thinking skills. Ability to break complex problems into understandable components. Hands on experience with generative AI and modern AI development tools. Ability to translate business concepts into technical instructions and workflows. Excellent Markdown, documentation, and written communication skills. Understanding of APIs, tools, integrations, structured data, and testing. Ability to collaborate across business and technology teams. Comfort operating in ambiguity and continuously learning."
Pay: "A reasonable estimate of the current range for this role in the U.S. is $90,000 - $154,00.00." Note typo double zero; we preserve as is.
We must not include EEO etc.
Now produce HTML fragment:
About the role
This is a hybrid role. Infinitive is a data and AI consultancy that helps clients modernize, monetize, and operationalize their data to generate lasting value. They pride themselves on their deep industry and technology expertise, ensuring that they drive and sustain the adoption of new capabilities. Infinitive is committed to aligning their team with their clients' culture, ensuring a successful partnership by bringing the right mix of talent and skills for high return on investment. Infinitive has earned recognition as one of the "Best Small Firms to Work For" by Consulting Magazine, receiving this accolade nine times, most recently in 2026. They have also been honored as a “Top Workplace” by the Washington Post, “Best Places to Work” by the Washington Business Journal, and “Best Places to Work” by Virginia Business.
Responsibilities
- Business Process Transformation Lead discovery with executives, business teams, subject matter experts, analysts, and engineers. Decompose complex processes into steps, decisions, inputs, outputs, rules, dependencies, and exceptions. Identify bottlenecks, repetitive work, knowledge gaps, and inefficient handoffs. Challenge legacy process assumptions and design future state workflows around AI enabled capabilities. Create practical roadmaps that connect prototypes to scalable operating models.
- Prompt and Context Engineering Design system prompts, task prompts, reusable instructions, and multi step prompt workflows. Translate requirements, policies, and expert knowledge into explicit instructions, constraints, examples, and escalation conditions. Define structured output formats that people and downstream systems can consume reliably. Determine what context should be persistent, retrieved dynamically, or supplied by the user. Optimize model context for quality, speed, cost, and maintainability.
- MCP Tools and Handler Engineering Design MCP servers, clients, and reusable tools where they improve access to enterprise capabilities. Create clear tool descriptions, efficient parameters, structured responses, and predictable handler behavior. Connect AI applications with APIs, databases, applications, knowledge repositories, and data platforms. Plan permissions, authentication, governance, logging, error handling, and recovery. Define when AI may act, when it should recommend, and when a human must approve.
- Markdown and Knowledge Architecture Create AGENTS.md, CLAUDE.md, README.md, business rules, prompt libraries, process definitions, data dictionaries, tool documentation, architecture notes, and evaluation cases. Organize large amounts of information so both humans and AI can navigate it efficiently. Use hierarchy, references, examples, rules, and exceptions to create durable and reusable context. Manage cross document relationships and reduce unnecessary token consumption.
- AI Agents and Workflow Engineering Design agentic workflows that can plan
Requirements
with Preferred Experience content.Qualifications
with the Qualifications bullet list. Skills maybe not separate; we could omit if no distinct skills section beyond qualifications. Pay: we have compensation range: $90,000 - $154,000.00 (note typo double zero). We'll include Pay section. Schedule: not mentioned; hybrid role indicates hybrid work but not schedule specifics. Should we include Schedule? The rule: only include section if posting has real, specific content. Hybrid role indicates hybrid work arrangement but not schedule like full-time/part-time. Might be considered schedule? Probably not enough detail; we can omit Schedule. Benefits: not mentioned; omit. Thus sections: About the role, Responsibilities, Requirements, Qualifications, Pay. We need to preserve all substantive information, not invent or summarize away detail. Must not include boilerplate like EEO etc. Remove that. We need to include the company description under About the role. Also mention hybrid role. Let's extract content: About Infinitive paragraph: "Infinitive is a data and AI consultancy that helps clients modernize, monetize, and operationalize their data to generate lasting value. They pride themselves on their deep industry and technology expertise, ensuring that they drive and sustain the adoption of new capabilities. Infinitive is committed to aligning their team with their clients' culture, ensuring a successful partnership by bringing the right mix of talent and skills for high return on investment. Infinitive has earned recognition as one of the "Best Small Firms to Work For" by Consulting Magazine, receiving this accolade nine times, most recently in 2026. They have also been honored as a “Top Workplace” by the Washington Post, “Best Places to Work” by the Washington Business Journal, and “Best Places to Work” by Virginia Business." Also first line: "This is a hybrid role". Could include that. Thus About the role: combine hybrid role statement and company overview. Responsibilities: list from "What You Will Do:" with subheadings? The content includes multiple sub-sections: Business Process Transformation, Prompt and Context Engineering, MCP Tools and Handler Engineering, Markdown and Knowledge Architecture, AI Agents and Workflow Engineering, AI Evaluation and Quality, Critical Thinking Is the Core Capability (maybe part of responsibilities). Also includes "Example Engagement", "What Success Looks Like". Those are also responsibilities/outcomes. We need to preserve all substantive information; we can turn each bullet into- and
. We can embed inside
- ? Not prohibited but maybe safer to keep plain text. We'll produce
- items each starting with the heading. Thus we need to split the responsibilities into items: - Business Process Transformation Lead discovery with executives, business teams, subject matter experts, analysts, and engineers. Decompose complex processes into steps, decisions, inputs, outputs, rules, dependencies, and exceptions. Identify bottlenecks, repetitive work, knowledge gaps, and inefficient handoffs. Challenge legacy process assumptions and design future state workflows around AI enabled capabilities. Create practical roadmaps that connect prototypes to scalable operating models. - Prompt and Context Engineering Design system prompts, task prompts, reusable instructions, and multi step prompt workflows. Translate requirements, policies, and expert knowledge into explicit instructions, constraints, examples, and escalation conditions. Define structured output formats that people and downstream systems can consume reliably. Determine what context should be persistent, retrieved dynamically, or supplied by the user. Optimize model context for quality, speed, cost, and maintainability. - MCP Tools and Handler Engineering Design MCP servers, clients, and reusable tools where they improve access to enterprise capabilities. Create clear tool descriptions, efficient parameters, structured responses, and predictable handler behavior. Connect AI applications with APIs, databases, applications, knowledge repositories, and data platforms. Plan permissions, authentication, governance, logging, error handling, and recovery. Define when AI may act, when it should recommend, and when a human must approve. - Markdown and Knowledge Architecture Create AGENTS.md, CLAUDE.md, README.md, business rules, prompt libraries, process definitions, data dictionaries, tool documentation, architecture notes, and evaluation cases. Organize large amounts of information so both humans and AI can navigate it efficiently. Use hierarchy, references, examples, rules, and exceptions to create durable and reusable context. Manage cross document relationships and reduce unnecessary token consumption. - AI Agents and Workflow Engineering Design agentic workflows that can plan, retrieve, reason, call tools, and request input. Define authorization boundaries, memory and state, failure recovery, escalation, and human checkpoints. Develop reusable components that support multiple use cases. Use modern AI tools to prototype, document, test, troubleshoot, and accelerate implementation. - AI Evaluation and Quality Define measurable acceptance criteria and representative evaluation datasets. Test accuracy, consistency, unsupported claims, latency, token use, and cost. Compare models, prompting strategies, tool designs, and workflow alternatives. Analyze failures across the model, prompt, context, data, tool, workflow, and process layers. Build feedback loops that improve the solution over time. - Critical Thinking Is the Core Capability AI models and tools will continue to change. The enduring capability for this role is the ability to structure difficult problems, test assumptions, and select the simplest reliable approach. Strong candidates naturally ask questions such as: What outcome are we actually trying to achieve? Why does this process exist and which steps create value? What information is required and is it trustworthy? Which decisions are deterministic and which require judgment? What assumptions are we making? How should the system behave when evidence is incomplete or contradictory? What actions can AI safely perform? What is the simplest architecture capable of producing the required outcome? - Example Engagement A team spends hours reviewing customer requests, policies, transaction data, and historical cases before making a recommendation. The AI Transformation Engineer redesigns the process, defines the data and tools required, creates prompts and durable Markdown instructions, and establishes validation and human decision points. Request → Gather Context → Retrieve Data → Apply Rules → Analyze → Recommend → Human Review → Execute → Learn - What Success Looks Like Success is measured by better business and engineering outcomes, not by the number of prompts, models, or prototypes produced. Expected results may include: Faster and more reliable business processes Reduced manual work and process complexity More consistent analysis and decisions Faster delivery of AI enabled products and services Better employee and customer experiences Improved data utilization and knowledge access Lower operating cost with appropriate controls Organizations operating differently because of AI We need to keep all that. Now Requirements: Preferred Experience bullet list: "Strong candidates may come from consulting, business analysis, process engineering, product management, solution architecture, software engineering, data engineering, automation, or operations. Experience with several of the following is preferred: Large Language Models, agents, and AI assisted development Prompt engineering and context engineering MCP servers, clients, tools, and handlers Function calling, APIs, and integration design RAG, vector search, and semantic retrieval Python, SQL, JSON, YAML, Markdown, and Git Databricks, cloud, or enterprise data platforms Business transformation, consulting, architecture, process, product, data, or software engineering" We can make each bullet maybe separate lines but it's okay as one
- with the whole text. Qualifications bullet list: "Strong analytical and critical thinking skills. Ability to break complex problems into understandable components. Hands on experience with generative AI and modern AI development tools. Ability to translate business concepts into technical instructions and workflows. Excellent Markdown, documentation, and written communication skills. Understanding of APIs, tools, integrations, structured data, and testing. Ability to collaborate across business and technology teams. Comfort operating in ambiguity and continuously learning." Pay: "A reasonable estimate of the current range for this role in the U.S. is $90,000 - $154,00.00." Note typo double zero; we preserve as is. We must not include EEO etc. Now produce HTML fragment:
About the role
This is a hybrid role. Infinitive is a data and AI consultancy that helps clients modernize, monetize, and operationalize their data to generate lasting value. They pride themselves on their deep industry and technology expertise, ensuring that they drive and sustain the adoption of new capabilities. Infinitive is committed to aligning their team with their clients' culture, ensuring a successful partnership by bringing the right mix of talent and skills for high return on investment. Infinitive has earned recognition as one of the "Best Small Firms to Work For" by Consulting Magazine, receiving this accolade nine times, most recently in 2026. They have also been honored as a “Top Workplace” by the Washington Post, “Best Places to Work” by the Washington Business Journal, and “Best Places to Work” by Virginia Business.
Responsibilities
- Business Process Transformation Lead discovery with executives, business teams, subject matter experts, analysts, and engineers. Decompose complex processes into steps, decisions, inputs, outputs, rules, dependencies, and exceptions. Identify bottlenecks, repetitive work, knowledge gaps, and inefficient handoffs. Challenge legacy process assumptions and design future state workflows around AI enabled capabilities. Create practical roadmaps that connect prototypes to scalable operating models.
- Prompt and Context Engineering Design system prompts, task prompts, reusable instructions, and multi step prompt workflows. Translate requirements, policies, and expert knowledge into explicit instructions, constraints, examples, and escalation conditions. Define structured output formats that people and downstream systems can consume reliably. Determine what context should be persistent, retrieved dynamically, or supplied by the user. Optimize model context for quality, speed, cost, and maintainability.
- MCP Tools and Handler Engineering Design MCP servers, clients, and reusable tools where they improve access to enterprise capabilities. Create clear tool descriptions, efficient parameters, structured responses, and predictable handler behavior. Connect AI applications with APIs, databases, applications, knowledge repositories, and data platforms. Plan permissions, authentication, governance, logging, error handling, and recovery. Define when AI may act, when it should recommend, and when a human must approve.
- Markdown and Knowledge Architecture Create AGENTS.md, CLAUDE.md, README.md, business rules, prompt libraries, process definitions, data dictionaries, tool documentation, architecture notes, and evaluation cases. Organize large amounts of information so both humans and AI can navigate it efficiently. Use hierarchy, references, examples, rules, and exceptions to create durable and reusable context. Manage cross document relationships and reduce unnecessary token consumption.
- AI Agents and Workflow Engineering Design agentic workflows that can plan