AI Engineer 5 (Gen AI Platform Services - Agentic Systems)
for section headings. Use - for any list of duties/requirements/benefits. Use
for prose.
We must not repeat job title as heading. Not include Job ID.
We must preserve ALL substantive information; do not invent or summarize away detail. That means we need to keep all details, not omit any. However we can combine similar info but must not lose detail. That is tricky: we need to keep all specifics like bullet points, salary numbers per location, benefits description, etc.
We need to output only HTML fragment, no /, no markdown fences.
We must ensure we don't include boilerplate like EEO, equal-opportunity, scam-warning, etc. Also remove duplicated lines, application instructions (like "No agencies please." "This role is expected to accept applications for a minimum of 5 business days." etc). Also remove "Learn more at the Capital One Careers website." etc. Also remove "Eligibility varies based on full or part-time status..." etc. Also remove "Capital One promotes a drug-free workplace." etc. Also remove "Capital One will consider for employment qualified applicants with a criminal history..." etc. Also remove accommodation contact lines. Also remove technical support email. Also remove disclaimer about third-party. Also remove Capital One Financial entities note.
We must keep substantive info: overview, team description, responsibilities, ideal candidate traits, basic qualifications, preferred qualifications, salary ranges, benefits, performance based incentive compensation, sponsorship for employment authorization.
We need to decide how to structure.
Potential sections:
- About the role: combine Overview and Team Description (prose). Could be two paragraphs.
- Responsibilities: list from "What You’ll Do:" each sentence as bullet.
- Requirements: Basic Qualifications (education + experience). Could be a list? It's a sentence with alternatives. Could be prose.
- Qualifications: Preferred Qualifications (list). Could be bullet list.
- Skills: maybe we could extract technical skills from Preferred Qualifications (like Python, Go, etc). But Preferred Qualifications already includes many technical skills; we could treat that as Skills section. However we already have Qualifications section for Preferred Qualifications. The instruction says use sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. So we need to map content to these headings. We can decide:
- About the role: Overview + Team Description.
- Responsibilities: What You’ll Do.
- Requirements: Basic Qualifications.
- Qualifications: Preferred Qualifications (maybe treat as qualifications).
- Skills: maybe we could list specific technical skills from Preferred Qualifications (like Python, Go, Scala, CUDA, Java, etc). But that would duplicate content. However we must preserve all substantive info; we could keep Preferred Qualifications as Qualifications and then Skills could be empty? But we cannot emit a heading with filler/placeholder text. So we should not include Skills if we don't have specific content beyond what's already covered. However we could extract a list of skills like "Python, Go, Scala, CUDA, Java, C++, C#, etc." but that is already in Preferred Qualifications. To avoid duplication, we could still include Skills as a list of those specific technologies, but we would be repeating content. The instruction says preserve ALL substantive information; does not forbid duplication? It says do NOT invent or summarize away detail. Duplication might be okay but could be considered redundant. However better to avoid duplication and just not include Skills if we don't have distinct content. But we need to follow the instruction: "Prefer a few substantive sections over many thin ones." So we can omit Skills if not needed.
- Benefits: from benefits paragraph plus performance based incentive compensation.
- Pay: salary ranges per location plus sponsorship note? Sponsorship is not pay but maybe part of compensation. Could include in Pay.
- Schedule: none, omit.
Thus sections: About the role, Responsibilities, Requirements, Qualifications, Benefits, Pay.
We need to ensure we include all substantive info from the posting.
Let's extract each piece.
Overview paragraph:
"At Capital One, we are creating responsible and reliable AI systems, changing banking for good. For years, Capital One has been an industry leader in using machine learning to create real-time, personalized customer experiences. Our investments in technology infrastructure and world-class talent — along with our deep experience in machine learning — position us to be at the forefront of enterprises leveraging AI. From informing customers about unusual charges to answering their questions in real time, our applications of AI & ML are bringing humanity and simplicity to banking. We are committed to continuing to build world-class applied science and engineering teams to deliver our industry leading capabilities with breakthrough product experiences and scalable, high-performance AI infrastructure. At Capital One, you will help bring the transformative power of emerging AI capabilities to reimagine how we serve our customers and businesses who have come to love the products and services we build."
Team Description paragraph:
"The Intelligent Foundations and Experiences (IFX) team is at the center of bringing our vision for AI at Capital One to life. We work hand-in-hand with our partners across the company to advance the state of the art in science and AI engineering, and we build and deploy proprietary solutions that are central to our business and deliver value to millions of customers. Our AI models and platforms empower teams across Capital One to enhance their products with the transformative power of AI, in responsible and scalable ways for the highest leverage impact."
We can combine into About the role.
Responsibilities: "What You’ll Do:" list:
- Partner with a cross-functional team of engineers, research scientists, technical program managers, and product managers to deliver AI-powered products that change how our associates work and how our customers interact with Capital One.
- Design, develop, test, deploy, and support AI software components including foundation model training, large language model inference, agents and multi-agent workflows, similarity search, guardrails, model evaluation, experimentation, governance, and observability, etc.
- Leverage a broad stack of Open Source and SaaS AI technologies such as AWS Ultraclusters, Huggingface, VectorDBs, PyTorch, and more.
- Invent and introduce state-of-the-art foundation model optimization techniques to improve the performance — scalability, cost, latency, throughput — of large scale production AI systems.
- Contribute to the technical vision and the long term roadmap of foundational AI systems at Capital One.
- Design, implement and optimize multi-model orchestration pipelines - integrating LLMs, vector search, and domain-specific models into unified systems
- Establish and lead cost-performance governance reviews across AI systems, tracking GPU utilization, model throughput, and inference cost efficiency
- Lead team design councils or design review boards to ensure technical consistency and compliance with AI engineering standards
- Mentor Principal and Manager-level AI engineers, fostering cross-domain learning and elevating organizational technical maturity
We need to keep each as bullet.
Requirements: Basic Qualifications:
"Bachelor's degree in Computer Science, AI, Electrical Engineering, Computer Engineering, or related fields plus at least 6 years of experience developing AI and ML algorithms or technologies, or a Master's degree in Computer Science, AI, Electrical Engineering, Computer Engineering, or related fields plus at least 4 years of experience developing AI and ML algorithms or technologies
At least 6 years of experience programming with Python, Go, Scala, CUDA, or Java"
Note: The second line seems separate but it's part of Basic Qualifications. Actually the posting: "Basic Qualifications: Bachelor's degree ... plus at least 6 years ... or a Master's degree ... plus at least 4 years ... At least 6 years of experience programming with Python, Go, Scala, CUDA, or Java". So we have two bullet points: education+experience alternative, and programming experience.
We'll put as list.
Qualifications: Preferred Qualifications (list). Let's extract each bullet:
- Experience leading development AI systems with tradeoff decisions around cost, latency, throughput and accuracy
- 7 years of experience deploying scalable and responsible AI solutions on cloud platforms (e.g. AWS, Google Cloud, Azure, or equivalent private cloud)
- Experience designing, developing, delivering, and supporting complex AI systems
- Experience developing AI and ML algorithms or technologies (e.g. LLM Inference, Similarity Search and VectorDBs, Guardrails, Memory) using Python, C++, C#, Java, CUDA, or Golang
- Experience developing and applying state-of-the-art techniques for optimizing training and inference software to improve hardware utilization, latency, throughput, and cost
- Experience in building agentic AI systems and agentic workflows
- Passion for staying abreast of the latest AI research and AI systems, and judiciously apply novel techniques in production
- Excellent communication and presentation skills, with the ability to articulate complex AI concepts to peers
- Experience architecting and integrating heterogeneous AI systems - including rule-based, retrieval-augmented, and generative components - into unified production pipelines
- Experience defining and enforcing standards for ethical AI deployment, including explainability, fairness, and human-in-the-loop review processes
- Demonstrated ability to balance model performance and operational cost through dynamic inference strategies and model compression
- Experience right-sizing models, instance counts, and hardware types given requirements (e.g., context length, token inputs, token outputs)
We need to keep all.
Benefits: from paragraph:
"Capital One offers a comprehensive, competitive, and inclusive set of health, financial and other benefits that support your total well-being. Learn more at the Capital One Careers website. Eligibility varies based on full or part-time status, exempt or non-exempt status, and management level."
Also performance based incentive compensation: "This role is also eligible to earn performance based incentive compensation, which may include cash bonus(es) and/or long term incentives (LTI). Incentives could be discretionary or non discretionary depending on the plan."
Also sponsorship: "Capital One will consider sponsoring a new qualified applicant for employment authorization for this position."
We should keep these.
We should remove "Learn more at the Capital One Careers website." as it's basically a link instruction; maybe considered boilerplate? It's not exactly legal but could be considered application instruction? It's a reference to learn more; could be considered not substantive? The instruction says remove application instructions. This is not exactly application instruction but could be considered a referral. Safer to remove.
Also "Eligibility varies based on full or part-time status, exempt or non-exempt status, and management level." This is substantive about benefits eligibility; we should
for prose. We must not repeat job title as heading. Not include Job ID. We must preserve ALL substantive information; do not invent or summarize away detail. That means we need to keep all details, not omit any. However we can combine similar info but must not lose detail. That is tricky: we need to keep all specifics like bullet points, salary numbers per location, benefits description, etc. We need to output only HTML fragment, no /, no markdown fences. We must ensure we don't include boilerplate like EEO, equal-opportunity, scam-warning, etc. Also remove duplicated lines, application instructions (like "No agencies please." "This role is expected to accept applications for a minimum of 5 business days." etc). Also remove "Learn more at the Capital One Careers website." etc. Also remove "Eligibility varies based on full or part-time status..." etc. Also remove "Capital One promotes a drug-free workplace." etc. Also remove "Capital One will consider for employment qualified applicants with a criminal history..." etc. Also remove accommodation contact lines. Also remove technical support email. Also remove disclaimer about third-party. Also remove Capital One Financial entities note. We must keep substantive info: overview, team description, responsibilities, ideal candidate traits, basic qualifications, preferred qualifications, salary ranges, benefits, performance based incentive compensation, sponsorship for employment authorization. We need to decide how to structure. Potential sections: - About the role: combine Overview and Team Description (prose). Could be two paragraphs. - Responsibilities: list from "What You’ll Do:" each sentence as bullet. - Requirements: Basic Qualifications (education + experience). Could be a list? It's a sentence with alternatives. Could be prose. - Qualifications: Preferred Qualifications (list). Could be bullet list. - Skills: maybe we could extract technical skills from Preferred Qualifications (like Python, Go, etc). But Preferred Qualifications already includes many technical skills; we could treat that as Skills section. However we already have Qualifications section for Preferred Qualifications. The instruction says use sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. So we need to map content to these headings. We can decide: - About the role: Overview + Team Description. - Responsibilities: What You’ll Do. - Requirements: Basic Qualifications. - Qualifications: Preferred Qualifications (maybe treat as qualifications). - Skills: maybe we could list specific technical skills from Preferred Qualifications (like Python, Go, Scala, CUDA, Java, etc). But that would duplicate content. However we must preserve all substantive info; we could keep Preferred Qualifications as Qualifications and then Skills could be empty? But we cannot emit a heading with filler/placeholder text. So we should not include Skills if we don't have specific content beyond what's already covered. However we could extract a list of skills like "Python, Go, Scala, CUDA, Java, C++, C#, etc." but that is already in Preferred Qualifications. To avoid duplication, we could still include Skills as a list of those specific technologies, but we would be repeating content. The instruction says preserve ALL substantive information; does not forbid duplication? It says do NOT invent or summarize away detail. Duplication might be okay but could be considered redundant. However better to avoid duplication and just not include Skills if we don't have distinct content. But we need to follow the instruction: "Prefer a few substantive sections over many thin ones." So we can omit Skills if not needed. - Benefits: from benefits paragraph plus performance based incentive compensation. - Pay: salary ranges per location plus sponsorship note? Sponsorship is not pay but maybe part of compensation. Could include in Pay. - Schedule: none, omit. Thus sections: About the role, Responsibilities, Requirements, Qualifications, Benefits, Pay. We need to ensure we include all substantive info from the posting. Let's extract each piece. Overview paragraph: "At Capital One, we are creating responsible and reliable AI systems, changing banking for good. For years, Capital One has been an industry leader in using machine learning to create real-time, personalized customer experiences. Our investments in technology infrastructure and world-class talent — along with our deep experience in machine learning — position us to be at the forefront of enterprises leveraging AI. From informing customers about unusual charges to answering their questions in real time, our applications of AI & ML are bringing humanity and simplicity to banking. We are committed to continuing to build world-class applied science and engineering teams to deliver our industry leading capabilities with breakthrough product experiences and scalable, high-performance AI infrastructure. At Capital One, you will help bring the transformative power of emerging AI capabilities to reimagine how we serve our customers and businesses who have come to love the products and services we build." Team Description paragraph: "The Intelligent Foundations and Experiences (IFX) team is at the center of bringing our vision for AI at Capital One to life. We work hand-in-hand with our partners across the company to advance the state of the art in science and AI engineering, and we build and deploy proprietary solutions that are central to our business and deliver value to millions of customers. Our AI models and platforms empower teams across Capital One to enhance their products with the transformative power of AI, in responsible and scalable ways for the highest leverage impact." We can combine into About the role. Responsibilities: "What You’ll Do:" list: - Partner with a cross-functional team of engineers, research scientists, technical program managers, and product managers to deliver AI-powered products that change how our associates work and how our customers interact with Capital One. - Design, develop, test, deploy, and support AI software components including foundation model training, large language model inference, agents and multi-agent workflows, similarity search, guardrails, model evaluation, experimentation, governance, and observability, etc. - Leverage a broad stack of Open Source and SaaS AI technologies such as AWS Ultraclusters, Huggingface, VectorDBs, PyTorch, and more. - Invent and introduce state-of-the-art foundation model optimization techniques to improve the performance — scalability, cost, latency, throughput — of large scale production AI systems. - Contribute to the technical vision and the long term roadmap of foundational AI systems at Capital One. - Design, implement and optimize multi-model orchestration pipelines - integrating LLMs, vector search, and domain-specific models into unified systems - Establish and lead cost-performance governance reviews across AI systems, tracking GPU utilization, model throughput, and inference cost efficiency - Lead team design councils or design review boards to ensure technical consistency and compliance with AI engineering standards - Mentor Principal and Manager-level AI engineers, fostering cross-domain learning and elevating organizational technical maturity We need to keep each as bullet. Requirements: Basic Qualifications: "Bachelor's degree in Computer Science, AI, Electrical Engineering, Computer Engineering, or related fields plus at least 6 years of experience developing AI and ML algorithms or technologies, or a Master's degree in Computer Science, AI, Electrical Engineering, Computer Engineering, or related fields plus at least 4 years of experience developing AI and ML algorithms or technologies At least 6 years of experience programming with Python, Go, Scala, CUDA, or Java" Note: The second line seems separate but it's part of Basic Qualifications. Actually the posting: "Basic Qualifications: Bachelor's degree ... plus at least 6 years ... or a Master's degree ... plus at least 4 years ... At least 6 years of experience programming with Python, Go, Scala, CUDA, or Java". So we have two bullet points: education+experience alternative, and programming experience. We'll put as list. Qualifications: Preferred Qualifications (list). Let's extract each bullet: - Experience leading development AI systems with tradeoff decisions around cost, latency, throughput and accuracy - 7 years of experience deploying scalable and responsible AI solutions on cloud platforms (e.g. AWS, Google Cloud, Azure, or equivalent private cloud) - Experience designing, developing, delivering, and supporting complex AI systems - Experience developing AI and ML algorithms or technologies (e.g. LLM Inference, Similarity Search and VectorDBs, Guardrails, Memory) using Python, C++, C#, Java, CUDA, or Golang - Experience developing and applying state-of-the-art techniques for optimizing training and inference software to improve hardware utilization, latency, throughput, and cost - Experience in building agentic AI systems and agentic workflows - Passion for staying abreast of the latest AI research and AI systems, and judiciously apply novel techniques in production - Excellent communication and presentation skills, with the ability to articulate complex AI concepts to peers - Experience architecting and integrating heterogeneous AI systems - including rule-based, retrieval-augmented, and generative components - into unified production pipelines - Experience defining and enforcing standards for ethical AI deployment, including explainability, fairness, and human-in-the-loop review processes - Demonstrated ability to balance model performance and operational cost through dynamic inference strategies and model compression - Experience right-sizing models, instance counts, and hardware types given requirements (e.g., context length, token inputs, token outputs) We need to keep all. Benefits: from paragraph: "Capital One offers a comprehensive, competitive, and inclusive set of health, financial and other benefits that support your total well-being. Learn more at the Capital One Careers website. Eligibility varies based on full or part-time status, exempt or non-exempt status, and management level." Also performance based incentive compensation: "This role is also eligible to earn performance based incentive compensation, which may include cash bonus(es) and/or long term incentives (LTI). Incentives could be discretionary or non discretionary depending on the plan." Also sponsorship: "Capital One will consider sponsoring a new qualified applicant for employment authorization for this position." We should keep these. We should remove "Learn more at the Capital One Careers website." as it's basically a link instruction; maybe considered boilerplate? It's not exactly legal but could be considered application instruction? It's a reference to learn more; could be considered not substantive? The instruction says remove application instructions. This is not exactly application instruction but could be considered a referral. Safer to remove. Also "Eligibility varies based on full or part-time status, exempt or non-exempt status, and management level." This is substantive about benefits eligibility; we should