Senior AI Engineer

Senior AI Engineer

Working with Us Challenging. Meaningful. Life-changing. Those aren't words that are usually associated with a job. But working at Bristol Myers Squibb is anything but usual. Here, uniquely interesting work happens every day, in every department. From optimizing a production line to the latest breakthroughs in cell therapy, this is work that transforms the lives of patients, and the careers of those who do it. You'll get the chance to grow and thrive through opportunities uncommon in scale and scope, alongside high-achieving teams. Take your career farther than you thought possible.

Bristol Myers Squibb recognizes the importance of balance and flexibility in our work environment. We offer a wide variety of competitive benefits, services and programs that provide our employees with the resources to pursue their goals, both at work and in their personal lives.

As a Senior AI Engineer on the AI Venture Studio team, you will be a hands-on senior individual contributor who leans into artificial intelligence (AI) to design and build impactful solutions to transform patients' lives. This role is accountable for the AI-first engineering of cloud-native applications, agentic AI products, and the knowledge and context infrastructure that powers them. You will have access to the latest AI-centric tools and technologies to support activities such as the design of APIs and MCPs, cloud services orchestration, agent runtime deployment, workflow pipeline implementation, and reusable platform pattern development that enables AI Accelerator projects to move fast without giving up reliability, observability, security, or enterprise architectural alignment.

This role lives inside the AI Accelerator delivery model: six fully agile two-week sprints across a twelve-week cycle to build, test, validate, and prepare minimum viable products (MVPs) for broader organizational adoption and scaling. AI Accelerator projects focus on the most challenging and highest-upside pharma-specific problems across R&D, Commercialization, Manufacturing, and Enabling Functions where critical context is buried in unstructured knowledge files, multimodal documents and reports, operational records, and scientific evidence packages.

What Matters Most in This Role:

• Ship in cycles by demonstrating engineering progress and lessons learned every two weeks.
• Focus on AI-first solutioning that prioritizes BMS technology investments (AWS, Claude, LangSmith, etc.) with the best chance of meeting use case and project success metrics.
• Collaborate effectively with other engineers (AI, data, UI/UX, machine learning) and broader agile AI accelerator product teams.
• Demonstrate a curious and inquisitive mindset with broad technical adaptability while staying hands-on with frontier AI technologies, AI coding agents, and the latest agentic engineering capabilities.

Additional Key Responsibilities:

Cloud-Native Application and AI Engineering:

• Design, build, and deliver backend services and application components using Python/FastAPI, TypeScript/Node, or similar technologies that integrate LLM APIs, AI agents, retrieval systems, workflow engines, and enterprise systems to create scalable AI-powered solutions.
• Develop MCP-accessible services, tools, and skills that enable governed read, write, and search access to structured knowledge assets (e.g., Markdown, YAML), with versioning, auditability, and integration into cloud-native storage and identity patterns.
• Implement secure application patterns for authentication and authorization, including enterprise SSO, service-account and machine credential management, secrets management, input/schema validation, and secure service-to-service communication.
• Partner with frontend engineers throughout the software delivery lifecycle to define clean API contracts, streaming response patterns, error handling, and service-level behaviors that enable intuitive AI-powered user experiences.

Agent Engineering, Orchestration, and Knowledge Systems:

• Build and operate agentic applications using LangGraph, Claude Agent SDK, and related frameworks, including workflow state management, orchestration, tool use, loops, multi-agent collaboration, and durable execution patterns.
• Develop MCP servers, tools, and skills that expose governed enterprise capabilities to agents through secure, reusable, and observable interfaces.
• Design retrieval, memory, and context architectures using AWS-native services and data stores, including vector, graph, relational, cache, and object storage patterns that enable grounded and context-aware AI applications.
• Build evaluation, testing, and observability frameworks that measure agent quality, reliability, latency, cost, and business outcomes while enabling rapid iteration.
• Create reusable platform accelerators, deployment patterns, and golden paths for containerized, serverless, and production AI applications running on AWS.

Platform Engineering, DevOps, and Reliability:

• Build and maintain CI/CD pipelines, infrastructure-as-code, automated testing, evaluation frameworks, and release processes for cloud-native AI applications.
• Measure and improve reliability, quality, latency, cost, and business outcomes through observability, evaluation, and continuous delivery practices.
• Embed security, quality, and reliability controls into delivery pipelines, including automated testing, vulnerability scanning, regression suites, guardrails, and structured-output validation.
• Create isolated development and execution environments that support safe experimentation, reproducibility, auditability, and governed promotion of code and data assets.
• Develop and maintain reusable platform patterns, tooling, and engineering standards that accelerate the delivery of secure and scalable AI applications.

Technical Leadership, Collaboration, and Delivery:

• Translate business problems into technical architectures and delivery plans that align AI capabilities with measurable product outcomes.
• Drive MVPs toward production readiness by validating technical feasibility, reliability, scalability, security, and measurable business value.
• Rapidly prototype, validate, and iterate on emerging AI capabilities to identify scalable patterns and reduce technical uncertainty before broader adoption.
• Provide technical leadership through architecture reviews, code reviews, design mentorship, engineering standards, documentation, and reusable reference implementations.
• Communicate technical and cloud architecture trade-offs clearly, balancing speed, cost, reliability, security, compliance, scalability, and long-term maintainability.

Qualifications & Experience:

Required Qualifications:

• Bachelor's or higher degree in Computer Science, Engineering, Science, or a related field.
• 5+ years of experience designing, building, and scaling software applications, cloud platforms, APIs, or distributed systems with increasing technical responsibility.
• Strong proficiency in Python and FastAPI and/or TypeScript/Node, or comparable backend application frameworks.
• Hands-on experience building and operating cloud-native applications on AWS.
• Experience designing and delivering AI-powered applications that integrate LLMs, retrieval systems, workflows, agents, or other AI capabilities into real-world user experiences.
• Experience building agentic AI applications using frameworks such as LangGraph, LangChain, PydanticAI, Claude Agent SDK, or similar technologies.
• Experience with containers, CI/CD, GitHub-based workflows, automated testing, environment configuration, and infrastructure-as-code such as Terraform, AWS CDK, or CloudFormation.
• Practical experience integrating enterprise LLM services such as Anthropic (preferred), OpenAI, Gemini, Grok, AWS Bedrock, or similar enterprise-approved AI services into AI-powered applications.
• Demonstrated understanding of the architectural patterns, trade-offs, and engineering practices required to scale AI applications from prototype to production, including reliability, observability, security, performance, and cost management.
• Working knowledge of secure and responsible AI application patterns including authentication, authorization, enterprise SSO, secrets management, auditability, model evaluation, guardrails, and secure application architecture.
• Demonstrated ability to effectively use AI coding agents and AI-assisted development tools such as Claude Code, Codex, Gemini CLI, Cursor, Windsurf, or GitHub Copilot to accelerate software delivery.
• Strong communication skills and comfort operating within fast-moving, cross-functional agile teams where ambiguity, rapid experimentation, and continuous learning are expected.

Desired Qualifications:

• Experience building MCP servers, MCP tools, FastMCP applications, or governed agent tooling ecosystems.
• Experience designing retrieval, memory, context, and knowledge architectures using vector stores, relational databases, graph databases, and enterprise knowledge systems.
• Experience developing multi-agent systems, workflow orchestration patterns, tool-calling architectures, durable execution, and long-running agent workflows.
• Experience with evaluation-driven development, agent testing, benchmark creation, AI observability, and platforms such as LangSmith, promptfoo, or similar tooling.
• Experience designing semantic layers, natural-language-to-SQL systems, analytics agents, or governed data access patterns.
• Experience building sandboxed execution environments, provenance tracking, version-controlled data workflows, and audit-friendly agent architectures.
• Experience deploying,