Senior Staff AI Platform Engineer
$184,000–$253,000 year
RemoteUnited States
Job Summary
Design, build, and operate components of the AI Gateway including centralized identity, token budgeting, DLP, multi-model routing, and audit logging. Build and maintain the Harness layer for agent orchestration, prompt construction, memory management, and model abstraction across AWS Bedrock and Google Vertex. Develop production services in Python (FastAPI) and pydantic.ai, implement MCP/tool wiring for internal and SaaS-embedded agents, and contribute to the Claude and Gemini Enterprise plugin framework. Instrument the platform for observability including metrics, tracing, and audit trails, while participating in on-call and operational support. Write technical documentation, participate in architecture and code reviews, and partner with teams across Enterprise Data, Apps, and Infosec to integrate governed data sources. Work with the Sr. Director and model evaluation tooling to close the loop between evaluation results and routing decisions.
Required Qualifications
- 8 or more years of professional software engineering experience
- experience building or operating AI and ML infrastructure in a production environment
- Strong Python skills, ideally with FastAPI
- comfort picking up frameworks like pydantic.ai for LLM-powered components
- Solid software engineering fundamentals including clean, tested, production-grade code
- strong API design skills
- the ability to give and receive feedback well in code and architecture reviews
- Comfort operating in a fast-moving, still-forming platform environment
- energized by ambiguity
- enjoy turning a rough architecture into working, reliable infrastructure
Desired Qualifications
- Hands-on experience building production services that sit in front of multiple consumers such as an API gateway, internal platform, or data platform
- real exposure to authentication/authorization
- rate limiting
- observability
- audit logging
- direct AI and LLM platform experience
- Practical experience with agent orchestration frameworks (LangGraph or equivalent)
- calling hosted model providers such as AWS Bedrock or Google Vertex
- a working understanding of how context windows, memory, and tool-calling actually behave in production
- working familiarity with React and TypeScript
- Exposure to or curiosity about the Model Context Protocol (MCP)
- the challenges of governing tool access for agents operating across enterprise systems
- Familiarity with enterprise AI deployments such as Claude Enterprise (Anthropic) or Gemini Enterprise
- how they are administered
- how access and policy controls work
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.