Senior Application Engineer
Bristol Myers Squibb
6 days ago
Remote friendly (Seattle, WA)
United States
IT
Summary:
Senior Application Engineer (AI Venture Studio delivery team) responsible for building secure cloud-hosted applications, including agentic AI products and cross-functional knowledge/context infrastructure. Design APIs, services, infrastructure patterns, deployment pipelines, semantic-layer evolution patterns, and agent runtimes to support rapid MVP scaling with reliability, observability, security, and enterprise alignment.
Responsibilities:
- Design, build, and operate backend services/APIs powering AI Accelerator products.
- Develop Python/FastAPI or TypeScript/Node services integrating LLM APIs, retrieval, workflow engines, and enterprise systems.
- Execute 6 sprint cycles (6x 2-week sprints over 12 weeks) to build/test/validate MVP increments.
- Build MCP/FastMCP services for governed read/write/search over structured knowledge (markdown/YAML), with permissioning, audit trails, version control, and AWS-native storage/identity integrations.
- Implement secure authn/authz (BMS SSO, secrets management), input validation, and safe service boundaries.
- Build and host LangGraph agentic workflows (orchestration, checkpoints), retrieval/memory/context services, and semantic layers for SQL/natural-language-to-code.
- Create CI/CD, infrastructure-as-code, automated tests, observability (latency/cost/usage/tracing), evaluation/guardrails in pipelines, and sandboxed agent execution with provenance/versioning.
- Partner cross-functionally; provide technical coaching (design/code/architecture reviews) and communicate cloud trade-offs.
Qualifications/Skills:
- BS+ in CS/Engineering/Science or related.
- 5+ years software/backend/cloud/platform engineering.
- AWS-native cloud engineering; proficiency with S3, RDS/PostgreSQL, Athena, Redis, OpenSearch, Fargate, Lambda, IAM, VPC.
- Python/FastAPI and/or TypeScript/Node.
- Containers, CI/CD, GitHub workflows, automated testing, IaC (Terraform/CDK/CloudFormation).
- LLM/RAG/agentic AI frameworks (e.g., LangGraph/LangChain/PydanticAI/Claude Agent SDK).
- MCP/FastMCP, read-write-search APIs, vector/graph/structured context systems, structured output validation, evaluation-driven development.
- SQL/semantic layers; sandboxed execution/provenance/audit/access-control patterns.
- Experience integrating approved frontier LLMs via enterprise channels (e.g., OpenAI/Anthropic/Gemini/AWS Bedrock).
Benefits (explicit):
- Health coverage; wellbeing support; 401(k) and protection benefits (disability/life/insurance).
- Paid time off (flexible time off or specified vacation/holidays by location/role).
- Additional time off options and annual Global Shutdown (eligibility-based).
Application instructions:
If the role doesn’t perfectly match your resume, apply anyway.
Senior Application Engineer (AI Venture Studio delivery team) responsible for building secure cloud-hosted applications, including agentic AI products and cross-functional knowledge/context infrastructure. Design APIs, services, infrastructure patterns, deployment pipelines, semantic-layer evolution patterns, and agent runtimes to support rapid MVP scaling with reliability, observability, security, and enterprise alignment.
Responsibilities:
- Design, build, and operate backend services/APIs powering AI Accelerator products.
- Develop Python/FastAPI or TypeScript/Node services integrating LLM APIs, retrieval, workflow engines, and enterprise systems.
- Execute 6 sprint cycles (6x 2-week sprints over 12 weeks) to build/test/validate MVP increments.
- Build MCP/FastMCP services for governed read/write/search over structured knowledge (markdown/YAML), with permissioning, audit trails, version control, and AWS-native storage/identity integrations.
- Implement secure authn/authz (BMS SSO, secrets management), input validation, and safe service boundaries.
- Build and host LangGraph agentic workflows (orchestration, checkpoints), retrieval/memory/context services, and semantic layers for SQL/natural-language-to-code.
- Create CI/CD, infrastructure-as-code, automated tests, observability (latency/cost/usage/tracing), evaluation/guardrails in pipelines, and sandboxed agent execution with provenance/versioning.
- Partner cross-functionally; provide technical coaching (design/code/architecture reviews) and communicate cloud trade-offs.
Qualifications/Skills:
- BS+ in CS/Engineering/Science or related.
- 5+ years software/backend/cloud/platform engineering.
- AWS-native cloud engineering; proficiency with S3, RDS/PostgreSQL, Athena, Redis, OpenSearch, Fargate, Lambda, IAM, VPC.
- Python/FastAPI and/or TypeScript/Node.
- Containers, CI/CD, GitHub workflows, automated testing, IaC (Terraform/CDK/CloudFormation).
- LLM/RAG/agentic AI frameworks (e.g., LangGraph/LangChain/PydanticAI/Claude Agent SDK).
- MCP/FastMCP, read-write-search APIs, vector/graph/structured context systems, structured output validation, evaluation-driven development.
- SQL/semantic layers; sandboxed execution/provenance/audit/access-control patterns.
- Experience integrating approved frontier LLMs via enterprise channels (e.g., OpenAI/Anthropic/Gemini/AWS Bedrock).
Benefits (explicit):
- Health coverage; wellbeing support; 401(k) and protection benefits (disability/life/insurance).
- Paid time off (flexible time off or specified vacation/holidays by location/role).
- Additional time off options and annual Global Shutdown (eligibility-based).
Application instructions:
If the role doesn’t perfectly match your resume, apply anyway.