Senior Application Engineer Seattle WA

ATTENTION MILITARY AFFILIATED JOB SEEKERS- Our organization works with partner companies to source qualified talent for their open roles. The following position is available toVeterans Transitioning Military National Guard and Reserve Members Military Spouses Wounded Warriors and their Caregivers. If you have the required skill set education requirements and experience please click the submit button and follow the next steps. Unless specifically stated otherwise this role is On-Site at the location detailed in the job post.

Summary:

As a Senior Application Engineer within Bristol Myers Squibbs AI Venture Studio delivery team you will be a hands-on senior individual contributor responsible for building secure cloud-hosted applications including but not limited to agentic AI products and cross functional knowledge and context infrastructure. You will design APIs services infrastructure patterns deployment pipelines semantic-layer evolution patterns for agent context engineering and agent runtimes that allow AI Accelerator pods to move quickly without giving up reliability observability security or enterprise alignment.

The role is deeply tied to the AI Accelerator delivery model: six two-week sprints over a 12-week cycle to build test validate and prepare MVPs for scaling in a fully agile model. You will leverage the latest technologies to address pharma-specific unsolved problems across R&D Commercialization Manufacturing and Enabling Functions where critical context is buried in unstructured knowledge files multimodal documents and reports operational records scientific evidence packages and other evolving knowledge sources.

BMS is an AWS-first engineering environment for these products so you will default to AWS-native services and patterns while integrating BMS-preferred AI tools such as LangGraph FastMCP OpenSearch Amazon S3 Vectors Amazon Neptune PostgreSQL/RDS Redis AWS Fargate LangSmith and a variety of approved frontier LLM models and APIs.

This is a role for someone excited to work hands-on with the latest AI tools and frontier technologies pushing the limits of what technology can do to help BMS discover develop and deliver innovative medicines.


Key Responsibilities:

Cloud-Native Application and API Engineering:
Design build and operate backend services APIs and application components that power AI Accelerator products.

Develop Python/FastAPI TypeScript/Node or similar services that integrate LLM APIs retrieval systems workflow engines and internal enterprise systems.

Execute AI Accelerator cycles of six two-week sprints over a 12-week cycle by developing testing and validating cloud and agentic AI product increments.

Develop MCP-accessible services that allow approved agents to read write search and maintain structured (e.g. markdown/YAML) knowledge assets.

Build MCP/FastMCP read-write-search APIs permissioned knowledge stores version control audit trails access controls and integrations with AWS-native storage and identity patterns.

Implement secure application patterns for authn/authz BMS SSO BMS Cloud Creds secrets management auditability input validation and safe service boundaries.

Partner with frontend engineers to define clean API contracts streaming response patterns error handling and service-level behaviors for AI-powered user experiences.

Agent Runtime Retrieval and AWS Platform Patterns:
Build and host agentic workflows using LangGraph including workflow state multi-agent orchestration tool execution fan-out/fan-in patterns and durable checkpoints.

Develop MCP tool integrations and FastMCP servers that allow agents to use governed enterprise capabilities safely and consistently.

Implement retrieval memory and context services using AWS-aligned data stores such as S3 Athena PostgreSQL/RDS ElastiCache/Redis OpenSearch Amazon S3 Vectors and Amazon Neptune.

Build and evolve the semantic layer for SQL and other natural-language-to-code generating agents enabling novel analytical questions to be grounded in query history column values warehouse context explicit instructions memory and governed data tools.

Package reusable deployment patterns starter kits and golden paths for AWS Fargate serverless services containers and production-adjacent AI applications.

DevOps Infrastructure Observability and Evaluation:
Create and maintain CI/CD pipelines environment configuration automated tests infrastructure-as-code and release processes for cloud AI applications.

Instrument application reliability latency cost usage tracing and model/agent behavior using enterprise observability and AI evaluation tools such as LangSmith or similar platforms.

Embed automated quality gates security scans regression tests structured output validation gates and responsible AI guardrail checks into delivery pipelines.

Build sandboxed agent execution environments where code and data can branch together transformations are recoverable provenance is preserved and merge/audit workflows protect shared data assets.

Demonstrate MVP progress through bi-weekly demos and technical updates tracking platform performance reliability cost security and business-value signals to assess readiness for scaling.

Continuously improve shared platform patterns based on lessons learned across pods changing enterprise standards and advances in AI engineering practices.

Collaboration Enablement and Technical Leadership:
Partner with AI Engineers Data Engineers Data Scientists Frontend Engineers Pod Leads architects and product teams to solve complex delivery challenges.

Continuously refine delivery priorities and technical backlog items based on stakeholder feedback performance results sprint reviews and lessons learned throughout MVP development.

Help complete MVP transition activities by maturing AI capabilities adding key features validating reliability in practice confirming business value and assessing production readiness.

Provide technical coaching through design reviews code reviews architecture reviews incident learning documentation and reusable examples.

Communicate cloud trade-offs clearly including when to optimize for speed cost reliability compliance scalability or long-term maintainability.