AI Engineer, PDS BI&T

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. Read more: careers.bms.com/working-with-us.

Position Summary

The Senior Manager role will architect and develop autonomous multi-agent systems that power analytics, diagnostics, and decision support across Product Development and Supply. This role focuses on building graph-based orchestration workflows that combine LLM reasoning with business logic, real-time data integration, and enterprise security patterns.

You will design agent platforms that go beyond conversational interfaces to deliver autonomous analytical workflows, automated validations, and intelligent routing across diverse business domain

Position Responsibilities*

Key Responsibilities:

Multi-Agent System Architecture & Platform Development:

• Design and implement autonomous agent workflows using orchestration frameworks (LangGraph, CrewAI, Autogen, or similar)
• Build complex state machines with conditional routing, parallel execution, and error recovery patterns for analytical and diagnostic tasks
• Develop graph-based workflows with 10+ nodes involving agent collaboration, task decomposition, and sequential/parallel execution
• Create reusable agent node libraries and extensible platform patterns supporting multiple business domains
• Design versioning strategies and testing frameworks for agent workflows (unit, integration, end-to-end)

Backend Development & API Design:

• Build production FastAPI applications with async I/O patterns for PostgreSQL, Redis, and external services
• Implement Server-Sent Events (SSE) and WebSocket protocols for real-time agent streaming responses
• Design RESTful APIs and event-driven architectures for agent orchestration
• Develop robust error handling, graceful degradation, and enterprise security integration (LDAP, SSO, access control)
• Handle concurrent async operations and deploy containerized services using Docker and CI/CD pipelines

LLM Integration, Orchestration & Tool Calling:

• Integrate cloud-based LLM providers (AWS Bedrock, Azure OpenAI, Anthropic Claude, OpenAI GPT-4)
• Design prompt management systems with versioning, templating, and dynamic compilation
• Implement conversation state persistence using Redis checkpointing for multi-turn agent interactions
• Build tool-calling protocols (Model Context Protocol, function calling) for external data sources and APIs
• Develop response transformation pipelines converting raw data into structured analytical outputs (charts, insights)
• Create hybrid intelligence patterns combining LLM reasoning with rule-based logic and statistical analysis

LLMOps, Observability & Optimization:

• Integrate observability platforms (Langfuse, LangSmith, or similar) for end-to-end agent tracing and telemetry
• Build monitoring systems tracking agent performance, LLM usage, latency, costs, and quality metrics
• Implement evaluation frameworks measuring agent success rates, reasoning quality, and output accuracy
• Optimize token usage and manage LLM costs across production workflows

Cross-Functional Collaboration:

• Partner with data engineers and business analysts to translate requirements into agent workflows
• Collaborate with UX teams on streaming interfaces and visualization requirements
• Mentor junior engineers on async Python patterns, agent design, and LLMOps best practices
• Participate in architecture reviews and contribute to documentation and knowledge sharing

**Desired Experience*  Required:**

• Bachelor’s or Master’s degree in Computer Science, Engineering, AI, Data Science, or related fiel…