Senior Architect, Agentic AI for Marketing
NVIDIA · Santa Clara, CA · 1 mo ago
EngineeringFull-time
We need to output HTML fragment with sections: About the role? The posting includes description paragraphs. We need headings: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections with real specific content.
We need to parse the posting.
First paragraph: NVIDIA description, mission, etc. Could be "About the role"? Actually the role description: "We’re looking for a Senior Architect to help shape the next generation of Agentic AI platforms for NVIDIA Marketing." That's about the role. Then responsibilities: bullet list under "What You’ll Be Doing". Then requirements: "What We Need To See". Then ways to stand out: maybe "Skills" or "Preferred Qualifications". Benefits: mention equity and benefits, but not specifics. Pay: salary range given. Schedule: not mentioned. So we include About the role, Responsibilities, Requirements (maybe Qualifications), Skills (Ways to Stand Out), Benefits (mention equity and benefits), Pay (salary range). No Schedule.
We must not repeat job title as heading. No Job ID.
We must preserve all substantive info, not invent.
We need to use for section headings. Use
for section headings. Use - for any list of duties/requirements/benefits. Use
for prose.
We must remove boilerplate: EEO, equal opportunity, scam warning, cookie/navigation, application instructions (like "Applications for this job will be accepted at least until August 28, 2026." maybe that's not boilerplate? It's a date but could be considered application instruction? It says "Applications for this job will be accepted at least until August 28, 2026." That's not instruction to apply, just deadline. Might keep? The instruction says remove application instructions. This is a deadline, maybe considered application instruction. Safer to remove. Also "This posting is for an existing vacancy." maybe metadata, could drop. "NVIDIA uses AI tools in its recruiting processes." maybe drop. Also the list of protected classes etc drop. Also the trailing ", , JR2023829" drop.
We need to keep salary range: "The base salary range is 224,000 USD - 356,500 USD." Also mention equity and benefits.
We need to keep "You will also be eligible for equity and benefits." That's benefits.
We need to keep "Your base salary will be determined based on your location, experience, and the pay of employees in similar positions." That's also pay info.
We need to keep "NVIDIA is widely considered to be one of the technology world’s most desirable employers! We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!" That's fluff but maybe keep as part of About the role? It's generic marketing. Could be considered boilerplate? It's not EEO but still promotional. Might keep as part of About the role.
We need to ensure we don't invent.
Let's extract sections:
About the role: combine introductory paragraphs up to "We’re looking for a Senior Architect..." plus maybe the mission description. We'll produce a paragraph.
Responsibilities: list under "What You’ll Be Doing". Each bullet starts with a verb. We'll make
- .
Requirements: "What We Need To See" list. We'll make
- .
Skills: "Ways to Stand Out from the crowd:" list. We'll make
- .
Benefits: "You will also be eligible for equity and benefits." Could be a
.
Pay: salary range and base salary determination. Could be a
or two.
We must not include Schedule.
Let's craft HTML.
We need to ensure no extra whitespace? It's fine.
We'll output:
About the role
...
Responsibilities
- ...
...
Requirements
- ...
...
Skills
- ...
...
Benefits
You will also be eligible for equity and benefits.
Pay
Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 224,000 USD - 356,500 USD.
Check that we didn't miss any substantive info: The description about NVIDIA transforming computer graphics etc. Should we include that in About the role? It's about company, not role. Might be considered boilerplate but it's substantive about NVIDIA. The instruction: preserve ALL substantive information; do NOT invent or summarize away detail. So we should keep that description. It's not boilerplate like EEO. It's about NVIDIA's legacy. So include in About the role.
Thus About the role paragraph: combine first few sentences: "NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology—and amazing people. Today, we’re tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work. Come join the team and see how you can make a lasting impact on the world. We’re looking for a Senior Architect to help shape the next generation of Agentic AI platforms for NVIDIA Marketing. In this role, you’ll combine technical leadership with hands-on engineering. You’ll translate marketing opportunities—including personalization, customer journeys, content intelligence, recommendations, campaign operations, and field enablement—into reliable AI agents and reusable platform capabilities. You’ll join a team with strong foundations in recommendation systems, retrieval-augmented generation (RAG), embedding-based retrieval, model evaluation, conversational AI, model adaptation, and production infrastructure. Your role will be to provide senior technical architecture, business translation, and platform leadership, helping the team evolve from high-value AI applications into a durable agentic AI ecosystem for Marketing. Our team works at the intersection of applied AI, agentic systems, marketing technology, enterprise data, and production platforms. You’ll have the opportunity to lead complex initiatives from early discovery through architecture, prototyping, evaluation, deployment, observability, governance, and scale."
That seems good.
Now Responsibilities list: extract each bullet from "What You’ll Be Doing". Let's list them:
- Lead the architecture and delivery of Agentic AI solutions that support NVIDIA Marketing, including personalization, content discovery, campaign intelligence, recommendations, internal copilots, workflow automation, and customer-facing AI experiences.
- Translate business and marketing needs into practical agent architectures, including goals, tools, retrieval, memory, planning, human-in-the-loop workflows, evaluation criteria, and production operating models.
- Advance NVIDIA Marketing’s agentic AI platform by building on capabilities such as agent-tool gateways, multi-agent orchestration, conversational data assistants, recommendation APIs, embedding pipelines, contextual retrieval, model adapters, catalog intelligence, and production AI infrastructure.
- Shape the platform roadmap across capabilities such as agent registries, tool catalogs, permission models, memory and state services, evaluation frameworks, observability, reusable agent patterns, and lifecycle management.
- Partner with engineers to design reliable interfaces for agent invocation, tool execution, response formats, memory, state management, and integrations with marketing platforms, analytics systems, chat experiences, and content repositories.
- Establish production practices for agentic systems across evaluation, regression testing, observability, latency, cost, reliability, safety, access controls, auditability, fallback behavior, and incident response.
- Guide technical tradeoffs across model quality, retrieval precision, inference cost, throughput, latency, personalization, data freshness, privacy, security, and business impact.
- Build prototypes, reference architectures, technical blueprints, and reusable components that help move promising ideas into scalable production systems.
Make each - .
Requirements list from "What We Need To See":
- A BS, MS, or PhD in Computer Science, AI/ML, Electrical Engineering, Data Science, a related technical field, or equivalent experience.
- 12+ years of experience in one or more areas such as software engineering, AI/ML engineering, solutions architecture, applied AI, data platforms, or large-scale production systems.
- Experience building and deploying applications involving LLMs, generative AI, RAG, recommendation systems, conversational AI, or agentic AI.
- Strong programming skills in Python, along with experience working with APIs, Linux environments, distributed systems, containers, cloud-native infrastructure, and production debugging.
- Understanding of agentic AI system design, including tool use, orchestration, planning, memory, retrieval, evaluation, guardrails, human approval, and failure handling.
- Experience designing integrations between AI agents and enterprise tools using approaches such as MCP, function calling, API gateways, or related interoperability patterns.
- Experience developing conversational AI experiences grounded in structured or semi-structured data. This may include text-to-SQL, intent classification, multi-turn dialogue, retrieval, or connections to live data sources.
- Experience with production AI or software infrastructure, such as model serving, Kubernetes, Docker, CI/CD, observability, monitoring, health checks, performance testing, or cost optimization.
- Demonstrated ownership of technical solutions across architecture, development, deployment, integration, and ongoing operations.
- Ability to navigate ambiguous business problems, translate them into technical approaches, and communicate effectively with both technical and non-technical audiences.
Make each
- .
Skills list from "Ways to Stand Out from the crowd:":
- Production multi-agent systems, agent runtimes, b frameworks, or tool-using agents.
- Agent frameworks such as NVIDIA NeMo Agent Toolkit, LangGraph, LlamaIndex, LangChain, CrewAI, Semantic Kernel, OpenAI Agents SDK, Google ADK, or similar technologies.
- NVIDIA AI software, including NIM, NeMo, NeMo Retriever, NeMo Guardrails, NeMo Agent Toolkit, Nemotron, Triton, NVIDIA AI Enterprise, or GPU-enabled Kubernetes environments.
- MCP or agent-tool interoperability, including authenticated tool routing, server registries, enterprise tool catalogs, or policy-aware agent gateways.
- Agent evaluation and observability, including traces, tool-call monitoring, offline and online evaluations, regression testing, quality dashboards, or business outcome measurement.
Make each
- .
Benefits: "You will also be eligible for equity and benefits." Could also mention "NVIDIA is widely considered to be one of the technology world’s most desirable employers! We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!" That's more about culture, maybe keep in About the role? Already we have a sentence about immersive environment etc. Could add that as part of About the role. But we already have a long paragraph; we could append that sentence. However it's somewhat generic but still substantive. I'd include it in About the role after the initial description maybe before "We’re looking for...". Let's incorporate: after "Come join the team and see how you can make a lasting impact on the world." Actually we have that sentence. Then we could add: "NVIDIA is widely considered to be one of the technology world’s most desirable employers! We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!" That seems okay.
Thus About the role paragraph will be longer.
Now Pay: we have two sentences: base salary determination and range. Combine.
Now ensure no extra sections like Schedule.
Now output HTML.
Check for any leftover boiler
for prose. We must remove boilerplate: EEO, equal opportunity, scam warning, cookie/navigation, application instructions (like "Applications for this job will be accepted at least until August 28, 2026." maybe that's not boilerplate? It's a date but could be considered application instruction? It says "Applications for this job will be accepted at least until August 28, 2026." That's not instruction to apply, just deadline. Might keep? The instruction says remove application instructions. This is a deadline, maybe considered application instruction. Safer to remove. Also "This posting is for an existing vacancy." maybe metadata, could drop. "NVIDIA uses AI tools in its recruiting processes." maybe drop. Also the list of protected classes etc drop. Also the trailing ", , JR2023829" drop. We need to keep salary range: "The base salary range is 224,000 USD - 356,500 USD." Also mention equity and benefits. We need to keep "You will also be eligible for equity and benefits." That's benefits. We need to keep "Your base salary will be determined based on your location, experience, and the pay of employees in similar positions." That's also pay info. We need to keep "NVIDIA is widely considered to be one of the technology world’s most desirable employers! We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!" That's fluff but maybe keep as part of About the role? It's generic marketing. Could be considered boilerplate? It's not EEO but still promotional. Might keep as part of About the role. We need to ensure we don't invent. Let's extract sections: About the role: combine introductory paragraphs up to "We’re looking for a Senior Architect..." plus maybe the mission description. We'll produce a paragraph. Responsibilities: list under "What You’ll Be Doing". Each bullet starts with a verb. We'll make
- .
Requirements: "What We Need To See" list. We'll make
- .
Skills: "Ways to Stand Out from the crowd:" list. We'll make
- .
Benefits: "You will also be eligible for equity and benefits." Could be a
. Pay: salary range and base salary determination. Could be a
or two. We must not include Schedule. Let's craft HTML. We need to ensure no extra whitespace? It's fine. We'll output:
About the role
...
Responsibilities
- ... ...
Requirements
- ... ...
Skills
- ... ...
Benefits
You will also be eligible for equity and benefits.
Pay
Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 224,000 USD - 356,500 USD.
Check that we didn't miss any substantive info: The description about NVIDIA transforming computer graphics etc. Should we include that in About the role? It's about company, not role. Might be considered boilerplate but it's substantive about NVIDIA. The instruction: preserve ALL substantive information; do NOT invent or summarize away detail. So we should keep that description. It's not boilerplate like EEO. It's about NVIDIA's legacy. So include in About the role. Thus About the role paragraph: combine first few sentences: "NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology—and amazing people. Today, we’re tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work. Come join the team and see how you can make a lasting impact on the world. We’re looking for a Senior Architect to help shape the next generation of Agentic AI platforms for NVIDIA Marketing. In this role, you’ll combine technical leadership with hands-on engineering. You’ll translate marketing opportunities—including personalization, customer journeys, content intelligence, recommendations, campaign operations, and field enablement—into reliable AI agents and reusable platform capabilities. You’ll join a team with strong foundations in recommendation systems, retrieval-augmented generation (RAG), embedding-based retrieval, model evaluation, conversational AI, model adaptation, and production infrastructure. Your role will be to provide senior technical architecture, business translation, and platform leadership, helping the team evolve from high-value AI applications into a durable agentic AI ecosystem for Marketing. Our team works at the intersection of applied AI, agentic systems, marketing technology, enterprise data, and production platforms. You’ll have the opportunity to lead complex initiatives from early discovery through architecture, prototyping, evaluation, deployment, observability, governance, and scale." That seems good. Now Responsibilities list: extract each bullet from "What You’ll Be Doing". Let's list them: - Lead the architecture and delivery of Agentic AI solutions that support NVIDIA Marketing, including personalization, content discovery, campaign intelligence, recommendations, internal copilots, workflow automation, and customer-facing AI experiences. - Translate business and marketing needs into practical agent architectures, including goals, tools, retrieval, memory, planning, human-in-the-loop workflows, evaluation criteria, and production operating models. - Advance NVIDIA Marketing’s agentic AI platform by building on capabilities such as agent-tool gateways, multi-agent orchestration, conversational data assistants, recommendation APIs, embedding pipelines, contextual retrieval, model adapters, catalog intelligence, and production AI infrastructure. - Shape the platform roadmap across capabilities such as agent registries, tool catalogs, permission models, memory and state services, evaluation frameworks, observability, reusable agent patterns, and lifecycle management. - Partner with engineers to design reliable interfaces for agent invocation, tool execution, response formats, memory, state management, and integrations with marketing platforms, analytics systems, chat experiences, and content repositories. - Establish production practices for agentic systems across evaluation, regression testing, observability, latency, cost, reliability, safety, access controls, auditability, fallback behavior, and incident response. - Guide technical tradeoffs across model quality, retrieval precision, inference cost, throughput, latency, personalization, data freshness, privacy, security, and business impact. - Build prototypes, reference architectures, technical blueprints, and reusable components that help move promising ideas into scalable production systems. Make each - . Requirements list from "What We Need To See": - A BS, MS, or PhD in Computer Science, AI/ML, Electrical Engineering, Data Science, a related technical field, or equivalent experience. - 12+ years of experience in one or more areas such as software engineering, AI/ML engineering, solutions architecture, applied AI, data platforms, or large-scale production systems. - Experience building and deploying applications involving LLMs, generative AI, RAG, recommendation systems, conversational AI, or agentic AI. - Strong programming skills in Python, along with experience working with APIs, Linux environments, distributed systems, containers, cloud-native infrastructure, and production debugging. - Understanding of agentic AI system design, including tool use, orchestration, planning, memory, retrieval, evaluation, guardrails, human approval, and failure handling. - Experience designing integrations between AI agents and enterprise tools using approaches such as MCP, function calling, API gateways, or related interoperability patterns. - Experience developing conversational AI experiences grounded in structured or semi-structured data. This may include text-to-SQL, intent classification, multi-turn dialogue, retrieval, or connections to live data sources. - Experience with production AI or software infrastructure, such as model serving, Kubernetes, Docker, CI/CD, observability, monitoring, health checks, performance testing, or cost optimization. - Demonstrated ownership of technical solutions across architecture, development, deployment, integration, and ongoing operations. - Ability to navigate ambiguous business problems, translate them into technical approaches, and communicate effectively with both technical and non-technical audiences. Make each
- . Skills list from "Ways to Stand Out from the crowd:": - Production multi-agent systems, agent runtimes, b frameworks, or tool-using agents. - Agent frameworks such as NVIDIA NeMo Agent Toolkit, LangGraph, LlamaIndex, LangChain, CrewAI, Semantic Kernel, OpenAI Agents SDK, Google ADK, or similar technologies. - NVIDIA AI software, including NIM, NeMo, NeMo Retriever, NeMo Guardrails, NeMo Agent Toolkit, Nemotron, Triton, NVIDIA AI Enterprise, or GPU-enabled Kubernetes environments. - MCP or agent-tool interoperability, including authenticated tool routing, server registries, enterprise tool catalogs, or policy-aware agent gateways. - Agent evaluation and observability, including traces, tool-call monitoring, offline and online evaluations, regression testing, quality dashboards, or business outcome measurement. Make each
- . Benefits: "You will also be eligible for equity and benefits." Could also mention "NVIDIA is widely considered to be one of the technology world’s most desirable employers! We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!" That's more about culture, maybe keep in About the role? Already we have a sentence about immersive environment etc. Could add that as part of About the role. But we already have a long paragraph; we could append that sentence. However it's somewhat generic but still substantive. I'd include it in About the role after the initial description maybe before "We’re looking for...". Let's incorporate: after "Come join the team and see how you can make a lasting impact on the world." Actually we have that sentence. Then we could add: "NVIDIA is widely considered to be one of the technology world’s most desirable employers! We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!" That seems okay. Thus About the role paragraph will be longer. Now Pay: we have two sentences: base salary determination and range. Combine. Now ensure no extra sections like Schedule. Now output HTML. Check for any leftover boiler
- .
Benefits: "You will also be eligible for equity and benefits." Could be a
- .
Skills: "Ways to Stand Out from the crowd:" list. We'll make