Senior Applied AI Engineer – Agent Runtime
DataSnipper · New York, NY · 1 mo ago
HybridEngineering$230k–$290k/yrFull-time
We need to output HTML fragment with sections: About the role? Actually the posting includes "The Role", "About DataSnipper", "What You Will Do", "What You Will Bring", "What We Expect", "What We Offer". Also compensation range given. Need to map to headings: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Use for each section heading. Only include sections that have real specific content. We have content for About the role (the initial "The Role" paragraph). Responsibilities: "What You Will Do". Requirements/Qualifications/Skills: "What You Will Bring" includes must-have and nice-to-have; we can split into Requirements (must-have) and Qualifications/Skills maybe. But we can combine. The instruction: Use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). We need to decide which sections to include based on content.
We have:
- About the role: yes.
- Responsibilities: "What You Will Do" (Agent Engineering, Evaluation & Quality, Reliability & Collaboration) -> yes.
- Requirements: Must-have list -> yes.
- Qualifications: maybe Nice-to-Have? Could be Qualifications or Skills. We'll treat Nice-to-Have as Qualifications.
- Skills: maybe we can include specific skills from Must-have? But we already have Requirements. Could also include Skills separate but might be thin. Better to combine Requirements and Qualifications. However instruction: Prefer a few substantive sections over many thin ones. So we could have About the role, Responsibilities, Requirements (including must-have and nice-to-have), Benefits, Pay. Schedule: we have hybrid mode (at least 3 days onsite) -> that's schedule info. So include Schedule.
Benefits: "What We Offer" includes many items: salary + stock, flexible PTO, medical/dental, 401K match, parental leave, company-sponsored lunch, hybrid mode (but that's schedule), impact, etc. So Benefits section.
Pay: Compensation Range: $230K - $290K.
We need to avoid repeating job title as heading. Not include Job ID etc.
We need to use
for each section heading. Only include sections that have real specific content. We have content for About the role (the initial "The Role" paragraph). Responsibilities: "What You Will Do". Requirements/Qualifications/Skills: "What You Will Bring" includes must-have and nice-to-have; we can split into Requirements (must-have) and Qualifications/Skills maybe. But we can combine. The instruction: Use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). We need to decide which sections to include based on content.
We have:
- About the role: yes.
- Responsibilities: "What You Will Do" (Agent Engineering, Evaluation & Quality, Reliability & Collaboration) -> yes.
- Requirements: Must-have list -> yes.
- Qualifications: maybe Nice-to-Have? Could be Qualifications or Skills. We'll treat Nice-to-Have as Qualifications.
- Skills: maybe we can include specific skills from Must-have? But we already have Requirements. Could also include Skills separate but might be thin. Better to combine Requirements and Qualifications. However instruction: Prefer a few substantive sections over many thin ones. So we could have About the role, Responsibilities, Requirements (including must-have and nice-to-have), Benefits, Pay. Schedule: we have hybrid mode (at least 3 days onsite) -> that's schedule info. So include Schedule.
Benefits: "What We Offer" includes many items: salary + stock, flexible PTO, medical/dental, 401K match, parental leave, company-sponsored lunch, hybrid mode (but that's schedule), impact, etc. So Benefits section.
Pay: Compensation Range: $230K - $290K.
We need to avoid repeating job title as heading. Not include Job ID etc.
We need to use - for any list of duties/requirements/benefits. Use
for prose.
We must preserve all substantive information, not invent or summarize away detail. Must not include boilerplate like EEO etc. The posting didn't have that.
We need to output only HTML fragment.
Let's craft:
About the role
The Role We are looking for a Senior Applied AI Engineer to join the Agent Runtime team behind Alwin, our new Agentic Automation Platform for audit and finance. Alwin agents run for long times, work through multi-step audit procedures over client evidence, and return finished work papers with every number traced back to source. Humans review and sign off. The runtime is the layer every agent depends on: the model access, the base system prompt and context, the tools (document extraction, retrieval, sandboxes, MCP integrations), the orchestration of agents and sub-agents, and the observability and evals that tell us whether an agent is performing to objective standards. You will own the applied AI half of that layer. Product teams build audit-specific agents on top of it; you decide how the base agent reasons, what tools it gets and at what abstraction, how it manages context over long horizons, and how we measure and hill-climb accuracy, speed and cost. This is a hands-on role in a small team with a large blast radius. Your work goes in front of hundreds of thousands of audit and finance professionals, and the problems are largely open: there is no playbook for production agents in a regulated domain, so you will help write it.
About DataSnipper
maybe not needed as heading? The instruction list didn't include About DataSnipper but we could treat as part of About the role? However we have a separate paragraph about DataSnipper. Could include as part of About the role or separate section "About the company". Not in list but we could still include as a section? The instruction says use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't forbid other headings but says use those for section headings. Probably better to stick to those headings. We could incorporate DataSnipper description into About the role paragraph. But we must preserve all substantive information; we can merge.
Thus About the role paragraph can include both the role description and DataSnipper info.
Let's combine: after role description, add "About DataSnipper DataSnipper is the Agentic Automation Platform for audit and finance..." etc.
Now Responsibilities: Responsibilities
then - items for each bullet.
We need to extract bullet points from "What You Will Do". It has sections: Agent Engineering (multiple sub-bullets), Evaluation & Quality, Reliability & Collaboration. We'll create list items for each sub-bullet.
Let's list:
- Own the base agents: system prompt, context engineering, memory and state management for tasks that span many turns and hours of execution
- Design how agents use the tool layer, including document extraction, retrieval, code and file sandboxes, and MCP integrations, choosing the right level of abstraction so agents handle edge cases without wasting effort on mechanical steps
- Implement agentic patterns such as sub-agent composition, planning modes, human-in-the-loop gates, and model routing across multiple providers
- Ship end-to-end: from prototype with our audit domain experts, through evaluation, to production on Alwin
- Define and build automatic processes that improve the agent continuously over time
- Keep costs under control and implement cost-efficient approaches to AI-centric workflows
- Extract signal from long agent trajectories: attribute outcomes to specific reasoning steps and tool calls, classify failure modes, and turn them into fixes
- Hill-climb accuracy, latency and token cost, and make the trade-offs explicit for the teams building on the runtime
- Instrument agent behaviour with our observability stack and use production traces to drive improvements
- Partner with Agent Experience teams, Document Intelligence and the AI Platform team to turn their needs into runtime capabilities that are self-service rather than a request queue
- Stay on the frontier: evaluate new models, techniques and agent patterns, and bring the ones that hold up into production
Now Requirements (must-have): list items.
- 5+ years of software engineering experience with strong, production-grade Python
- Experience shipping and operating an LLM-powered product in production: you have dealt with hallucinations, latency spikes, tool failures and cost explosions at scale, and can explain what broke and how you fixed it
- Hands-on experience building agentic systems: control loops, tool selection, planning versus execution, retries and fallbacks, not only prompt-and-parse pipelines
- Experience with evaluation: you have built datasets, run offline and online experiments, and used the results to make an AI system measurably better
- Fluency with LLM APIs and agent frameworks across more than one model provider
- Proficient with AI-assisted engineering and excited about working with coding agents daily
- Strong fundamentals in software architecture and system design, and a track record of reliable, well-tested delivery
- Excellent communication; you can work directly with auditors and product partners to define what "correct" means
Nice-to-have (Qualifications): list items.
- Experience with Durable workflow engines or long-running background task systems
- Experience with RAG and retrieval pipelines over large, messy document corpora
- Document AI: VLMs, OCR, structured extraction and their metrics
- Sandboxed code execution, MCP, or multi-agent orchestration in production
- Domain experience in audit, accounting or fintech
- Familiarity with OWASP GenAI security practices and working in a regulated, privacy-sensitive environment
What We Expect (maybe could be part of Requirements or separate? Could be "Expectations" but not in list. Could incorporate into Requirements or Qualifications. But we have enough sections. Could add a section "Expectations" but not in list; maybe better to incorporate into Requirements as soft skills. However we already have communication etc. Could add a separate section "Expectations" but risk thin. I'd incorporate into Requirements as additional bullet points.
But we already have communication. The expectations: Ownership, Growth Mindset, Collaboration, Adaptability, Judgment. We can add as bullet points under Requirements or maybe under a separate section "Expectations". Since not in list, maybe better to add as a subsection under Requirements? But we need to preserve all info. Could add a section "Expectations" but not in the given list; risk being considered thin? It's substantive. The instruction says use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't forbid other headings but suggests using those. I'd stick to those headings and place expectations under Requirements or Qualifications. I'll add them under Requirements as additional bullet points.
Now Benefits:
Benefits
list items from What We Offer.
- Excellent salary + stock participation plan
- Flexible paid time off
- Comprehensive medical and dental coverage
- 401K match
- Paid parental leave
- Company-sponsored lunch
- Hybrid mode of work (at least 3 days onsite in our New York City office) (but schedule maybe separate)
- Being part of one of the fastest-growing scale-ups in the Netherlands
- Make an impact by disrupting the finance industry with us
- A flexible and growing organization with lots of opportunities to learn and develop
- International working environment, with a team of friendly and driven colleagues
- Access to OpenUp and Talkspace, the mental health and wellness platform
- Multiple social activities for team building
Schedule: hybrid mode (at least 3 days onsite) - we can put under Schedule.
Pay: Compensation Range: $230K - $290K.
Now ensure we don't repeat job title. No markdown.
Let's craft HTML.
Be careful to escape any HTML special characters? Not needed.
We'll output:
About the role
... combined text ...
Responsibilities
- ...
...
Requirements
- ...
...
Qualifications
- ...
...
Benefits
- ...
...
Pay
Compensation Range: $230K - $290K
Schedule
Hybrid mode of work (at least 3 days onsite in our New York City office)
Check that we didn't miss any substantive info: The "What We Expect" items we incorporated into Requirements? We haven't added them yet. Let's add them under Requirements as additional bullet points after the must-have list.
Thus Requirements will include both must-have and expectations.
Now ensure we didn't duplicate any content: The "What We Offer" includes hybrid mode; we moved hybrid mode to Schedule but also listed in Benefits? We should avoid duplication. We'll keep hybrid mode only in Schedule, not in Benefits. So remove hybrid mode from Benefits list.
Now ensure we didn't miss any other benefits: "Excellent salary + stock participation plan" is pay but we have Pay section; we could keep salary in Benefits? But Pay section already covers compensation range; we could still mention salary + stock as benefit but it's redundant. Better to keep Pay separate and not duplicate salary in Benefits. So Benefits list excludes salary/stock.
Thus Benefits list:
- Flexible paid time off
- Comprehensive medical and dental coverage
- 401K match
- Paid parental leave
- Company-sponsored lunch
- Being part
for prose. We must preserve all substantive information, not invent or summarize away detail. Must not include boilerplate like EEO etc. The posting didn't have that. We need to output only HTML fragment. Let's craft:
About the role
The Role We are looking for a Senior Applied AI Engineer to join the Agent Runtime team behind Alwin, our new Agentic Automation Platform for audit and finance. Alwin agents run for long times, work through multi-step audit procedures over client evidence, and return finished work papers with every number traced back to source. Humans review and sign off. The runtime is the layer every agent depends on: the model access, the base system prompt and context, the tools (document extraction, retrieval, sandboxes, MCP integrations), the orchestration of agents and sub-agents, and the observability and evals that tell us whether an agent is performing to objective standards. You will own the applied AI half of that layer. Product teams build audit-specific agents on top of it; you decide how the base agent reasons, what tools it gets and at what abstraction, how it manages context over long horizons, and how we measure and hill-climb accuracy, speed and cost. This is a hands-on role in a small team with a large blast radius. Your work goes in front of hundreds of thousands of audit and finance professionals, and the problems are largely open: there is no playbook for production agents in a regulated domain, so you will help write it.
About DataSnipper
maybe not needed as heading? The instruction list didn't include About DataSnipper but we could treat as part of About the role? However we have a separate paragraph about DataSnipper. Could include as part of About the role or separate section "About the company". Not in list but we could still include as a section? The instruction says use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't forbid other headings but says use those for section headings. Probably better to stick to those headings. We could incorporate DataSnipper description into About the role paragraph. But we must preserve all substantive information; we can merge. Thus About the role paragraph can include both the role description and DataSnipper info. Let's combine: after role description, add "About DataSnipper DataSnipper is the Agentic Automation Platform for audit and finance..." etc. Now Responsibilities:Responsibilities
then- items for each bullet.
We need to extract bullet points from "What You Will Do". It has sections: Agent Engineering (multiple sub-bullets), Evaluation & Quality, Reliability & Collaboration. We'll create list items for each sub-bullet.
Let's list:
- Own the base agents: system prompt, context engineering, memory and state management for tasks that span many turns and hours of execution
- Design how agents use the tool layer, including document extraction, retrieval, code and file sandboxes, and MCP integrations, choosing the right level of abstraction so agents handle edge cases without wasting effort on mechanical steps
- Implement agentic patterns such as sub-agent composition, planning modes, human-in-the-loop gates, and model routing across multiple providers
- Ship end-to-end: from prototype with our audit domain experts, through evaluation, to production on Alwin
- Define and build automatic processes that improve the agent continuously over time
- Keep costs under control and implement cost-efficient approaches to AI-centric workflows
- Extract signal from long agent trajectories: attribute outcomes to specific reasoning steps and tool calls, classify failure modes, and turn them into fixes
- Hill-climb accuracy, latency and token cost, and make the trade-offs explicit for the teams building on the runtime
- Instrument agent behaviour with our observability stack and use production traces to drive improvements
- Partner with Agent Experience teams, Document Intelligence and the AI Platform team to turn their needs into runtime capabilities that are self-service rather than a request queue
- Stay on the frontier: evaluate new models, techniques and agent patterns, and bring the ones that hold up into production
Now Requirements (must-have): list items.
- 5+ years of software engineering experience with strong, production-grade Python
- Experience shipping and operating an LLM-powered product in production: you have dealt with hallucinations, latency spikes, tool failures and cost explosions at scale, and can explain what broke and how you fixed it
- Hands-on experience building agentic systems: control loops, tool selection, planning versus execution, retries and fallbacks, not only prompt-and-parse pipelines
- Experience with evaluation: you have built datasets, run offline and online experiments, and used the results to make an AI system measurably better
- Fluency with LLM APIs and agent frameworks across more than one model provider
- Proficient with AI-assisted engineering and excited about working with coding agents daily
- Strong fundamentals in software architecture and system design, and a track record of reliable, well-tested delivery
- Excellent communication; you can work directly with auditors and product partners to define what "correct" means
Nice-to-have (Qualifications): list items.
- Experience with Durable workflow engines or long-running background task systems
- Experience with RAG and retrieval pipelines over large, messy document corpora
- Document AI: VLMs, OCR, structured extraction and their metrics
- Sandboxed code execution, MCP, or multi-agent orchestration in production
- Domain experience in audit, accounting or fintech
- Familiarity with OWASP GenAI security practices and working in a regulated, privacy-sensitive environment
What We Expect (maybe could be part of Requirements or separate? Could be "Expectations" but not in list. Could incorporate into Requirements or Qualifications. But we have enough sections. Could add a section "Expectations" but not in list; maybe better to incorporate into Requirements as soft skills. However we already have communication etc. Could add a separate section "Expectations" but risk thin. I'd incorporate into Requirements as additional bullet points.
But we already have communication. The expectations: Ownership, Growth Mindset, Collaboration, Adaptability, Judgment. We can add as bullet points under Requirements or maybe under a separate section "Expectations". Since not in list, maybe better to add as a subsection under Requirements? But we need to preserve all info. Could add a section "Expectations" but not in the given list; risk being considered thin? It's substantive. The instruction says use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't forbid other headings but suggests using those. I'd stick to those headings and place expectations under Requirements or Qualifications. I'll add them under Requirements as additional bullet points.
Now Benefits:
Benefits
list items from What We Offer. - Excellent salary + stock participation plan - Flexible paid time off - Comprehensive medical and dental coverage - 401K match - Paid parental leave - Company-sponsored lunch - Hybrid mode of work (at least 3 days onsite in our New York City office) (but schedule maybe separate) - Being part of one of the fastest-growing scale-ups in the Netherlands - Make an impact by disrupting the finance industry with us - A flexible and growing organization with lots of opportunities to learn and develop - International working environment, with a team of friendly and driven colleagues - Access to OpenUp and Talkspace, the mental health and wellness platform - Multiple social activities for team building Schedule: hybrid mode (at least 3 days onsite) - we can put under Schedule. Pay: Compensation Range: $230K - $290K. Now ensure we don't repeat job title. No markdown. Let's craft HTML. Be careful to escape any HTML special characters? Not needed. We'll output:About the role
... combined text ...
Responsibilities
- ... ...
Requirements
- ... ...
Qualifications
- ... ...
Benefits
- ... ...
Pay
Compensation Range: $230K - $290K
Schedule
Hybrid mode of work (at least 3 days onsite in our New York City office)
Check that we didn't miss any substantive info: The "What We Expect" items we incorporated into Requirements? We haven't added them yet. Let's add them under Requirements as additional bullet points after the must-have list. Thus Requirements will include both must-have and expectations. Now ensure we didn't duplicate any content: The "What We Offer" includes hybrid mode; we moved hybrid mode to Schedule but also listed in Benefits? We should avoid duplication. We'll keep hybrid mode only in Schedule, not in Benefits. So remove hybrid mode from Benefits list. Now ensure we didn't miss any other benefits: "Excellent salary + stock participation plan" is pay but we have Pay section; we could keep salary in Benefits? But Pay section already covers compensation range; we could still mention salary + stock as benefit but it's redundant. Better to keep Pay separate and not duplicate salary in Benefits. So Benefits list excludes salary/stock. Thus Benefits list: - Flexible paid time off - Comprehensive medical and dental coverage - 401K match - Paid parental leave - Company-sponsored lunch - Being part