Senior Manager, PDS BI&T Architecture & Components

The Analytics & AI Enablement (A&AIE) Architecture & Components Team is a highly technical team responsible for defining how digital solutions are built, ensuring they are scalable, operable, and future-ready through PDS Aim Points, with ambitions to revolutionize PDS use of AI by 2030-2035. Rather than delivering individual use cases, this team establishes and stewards the shared architectural foundations and components - including those used for the foundational data pipelines, analytical models, and business-facing reports and dashboards - that enable broad, consistent execution across PDS., This senior individual-contributor role will architect and build the shared, full-stack platform that powers analytics, digital products, and digital workers across PDS. The role focuses on distributed, multi-service systems that combine an orchestration layer, autonomous agents, shared services, and a federated frontend into a single internal platform-as-a-service - treated as reusable foundations rather than one-off use cases.

You will work end to end, from async backend services and APIs through to modern web frontends, and you will design platforms that go beyond conversational interfaces to deliver autonomous analytical workflows, standardized tool-calling, and composable UI experiences. This is a deeply hands-on, principal-level technical authority role; you set the bar through architecture, reference implementations, and engineering excellence., Platform & Multi-Service System Architecture

• Architect distributed, multi-service platforms that orchestrate work across autonomous services and agents, with conditional routing, parallel execution, and error recovery.
• Design the platform as an internal SaaS/PaaS: shared SDKs, service contracts, and reusable components that solution teams consume rather than rebuild.
• Build graph-based orchestration workflows combining LLM reasoning, business logic, real-time data integration, and enterprise security patterns.
• Create reusable node/component libraries and extensible platform patterns supporting multiple business domains.

Backend Development & API Design

• Build production FastAPI (or similar) applications with async I/O patterns for persistence and external services.
• Implement Server-Sent Events (SSE) and WebSocket protocols for real-time streaming responses.
• Design APIs and event-driven architectures for orchestration and service-to-service communication.
• Develop robust error handling, graceful degradation, and enterprise security integration (SSO, access control), deploying containerized services via CI/CD.

Frontend & Unified Experience

• Build modern web frontends (e.g., React) and design micro-frontend / Module Federation composition so independently built modules form one coherent experience.
• Develop and steward a shared component library and design system used across the platform.
• Design AI-enhanced UI patterns for streaming responses, chat, and analytical/canvas visualization.

MCP Development & Dual-Intent Delivery

• Make MCP development and hosting a first-class platform capability, ensuring every solution is dual-intent: delivered both as a full-stack web experience and through Claude Desktop.
• Design, build, and host production MCP servers that expose platform services and tools so the same underlying capabilities power both the web UI and Claude Desktop, with no divergence between the two surfaces.
• Define golden-path patterns, templates, and shared MCP servers (tools, resources, prompts, transport, and authentication) that solution teams reuse to ship dual-intent solutions quickly.
• Establish MCP hosting, versioning, security, and operational standards for seamless, enterprise-grade integration with Claude Desktop.

LLM Integration, Orchestration & Tool Calling

• Integrate cloud LLM providers (AWS Bedrock or comparable) into platform services.
• Design prompt management with versioning, templating, and dynamic compilation.
• Implement conversation/state persistence (e.g., Redis checkpointing) for multi-turn workflows.
• Build standardized tool-calling that connects agents and external clients to data sources and services, with the Model Context Protocol as the primary integration surface.

Reusability, Observability & Optimization

• Treat internal developers as customers: provide golden-path templates, clear contracts, and documentation that accelerate delivery.
• Define standards for versioning, contracts, and backward compatibility across the component ecosystem.
• Integrate observability and tracing; build monitoring for performance, latency, cost, and quality, and optimize resource and token usage across production workflows.

Cross-Functional Collaboration

• Partner with cloud, AI, data, and UX engineers on the team to integrate full-stack work with infrastructure, agentic capabilities, and interaction design.
• Partner with Enterprise engineering and governance teams to align standards, controls, and shared services.
• Provide technical mentorship on solution patterns, system design, and platform best practices, and contribute to architecture reviews and documentation., * Designed distributed platforms with service orchestration, conditional logic, and state management.
• Developed and hosted production MCP servers with demonstrated adoption across capabilities.
• Delivered dual-intent solutions where the same services power both a web experience and an LLM/desktop client via MCP.
• Implemented standardized tool-calling for external system integration.
• Designed shared SDKs/contracts and managed API/contract evolution across many consumers.
• Prompt engineering at scale (templating, versioning, optimization) and understanding of agentic design patterns (ReAct, Plan-and-Execute, tool-use agents).
• Strong problem-solving, communication, and ability to set technical direction and influence in globally distributed teams., Where you work matters - because collaboration, innovation and patient impact happen in many settings. Our roles are structured across four work models: site-essential, site-by-design, field-based and remote-by-design. The model assigned to this role is based on its core responsibilities. Learn more at https://careers.bms.com/ways-of-working. (https://careers.bms.com/life-at-bms/ways-of-working/)

Supporting People with Disabilities

BMS is dedicated to ensuring that people with disabilities can excel through a transparent recruitment process, reasonable workplace accommodations/adjustments and ongoing support in their roles. Applicants can request a reasonable workplace accommodation/adjustment prior to accepting a job offer. If you require reasonable accommodations/adjustments in completing this application, or in any part of the recruitment process, direct your inquiries to adastaffingsupport@bms.com . Visit careers.bms.com/eeo-accessibility to access our complete Equal Employment Opportunity statement.

Candidate Rights

BMS will consider qualified applicants with arrest and conviction records, pursuant to applicable laws in your area.

• Bachelor’s or Master’s degree in Computer Science, Engineering, AI, Data Science, or a related field.
• 6+ years of software engineering experience with deep full-stack delivery, including production experience building LLM-powered or agentic applications.
• Strong Python, including async patterns (asyncio, async/await) and Python-based automation.
• Production experience with async web frameworks (FastAPI or similar), REST, and event-driven / streaming architectures (WebSocket/SSE, queues, streams).
• Strong working knowledge of modern web frontends (React) and micro-frontend / Module Federation composition; deep frontend and design-system expertise a strong plus.
• Experience designing distributed, multi-service systems with well-defined contracts between components, and building an internal platform, SaaS/PaaS, or shared developer platform.
• Experience with agentic orchestration frameworks (LangGraph preferred; LangChain, CrewAI, Autogen, or similar) and integration with cloud LLM providers (AWS Bedrock, Azure OpenAI, Anthropic, or OpenAI) , including onboarding and standardizing these frameworks for solution teams .
• Strong platform and cloud depth: Docker and Kubernetes / Amazon EKS, infrastructure-as-code (CloudFormation), Git and CI/CD, service mesh, policy-as-code (OPA/Gatekeeper), and production observability (e.g., Prometheus, Grafana, Loki) on AWS (Azure and/or GCP a plus).
• Experience owning platform governance, security, and self-service onboarding for a shared platform - IAM/SSO, group-based authorization, and policy-as-code - acting as a technical gatekeeper for the teams that consume it., * Prior experience in global life sciences, pharma, or supply chain - especially in Product Development & Supply (PDS).
• Experience in regulated environments (GxP, GDPR, PII) and embedding compliance into platform design.
• Experience scaling an internal platform across multiple product/domain teams and managing the resulting contract and dependency surface.
• Experience working internationally with globally dispersed teams., * Excellent communication skills and the ability to influence technical decisions without direct authority.
• Hands-on experience implementing Agentic AI solutions and/or MCP is preferred.
• Relevant cloud certification (e.g., AWS) is a plus.

Subject to the terms and conditions of the applicable plans then in effect, you may be eligible to participate in our comprehensive benefit plans - including wellbeing support, retirement and financial protection benefits, and insurance offerings (medical, dental, vision, life and disability).

U.S.-based exempt employees are eligible for Flexible Time Off (FTO), which provides paid time off without a set accrual limit, subject to manager approval, along with 11 paid company holidays each year.

Non-exempt employees, RayzeBio employees, and employees located in Puerto Rico receive 160 hours of paid vacation annually for new hires (subject to manager approval), 11 paid company holidays, and 3 optional holidays.

Depending on eligibility, employees may also have access to additional time-off benefits, including paid sick leave, up to two paid volunteer days per year, summer hours flexibility, and leaves of absence for medical, personal, parental, caregiver, bereavement, or military needs. Eligible employees also enjoy an annual Global Shutdown between Christmas Day and New Year’s Day.

U.S.-based job seekers can explore full benefit offerings at https://careers.bms.com/benefits

At Bristol Myers Squibb, our employees often ask, “Who are you working for?”-a question that fuels collaboration, accountability, and urgency in our work. Our purpose-driven culture inspires us to discover, develop, and deliver innovative medicines to prevail over serious diseases. We offer uniquely interesting and meaningful work, opportunities for growth, and a supportive environment that values inclusion, wellbeing, flexibility, and comprehensive benefits. This is work that transforms the lives of patients, and the careers of those who do it.