Principal AI Platform Engineer

Title:
Prinicipal AI Engineer

Location:
Sunnyvale, California.

Duration: 6 to 12+ Months

Job Description:

Skill Proficiency Why It's Needed

Python (Advanced) Expert DSPy, FastAPI, async/await, MCP protocol

LLM/Agent Systems Strong ReAct patterns, prompt engineering, token optimization

Distributed Systems Strong MCP client-server, streaming (SSE), event-driven

API Design Strong REST, gRPC, API versioning, contract-first

Observability Strong Open Telemetry, distributed tracing, Prometheus

Databases Proficient Postgre

SQL, embeddings/vector search

Cloud/Infrastructure Proficient GCP (Big Query, GCS), Kubernetes, CCM

Integration & Data:

Skill Proficiency Why It's Needed

Upstream/Downstream APIs Strong Supplier Hub, SDE, MSO Buyplan, One Track

Data Pipeline Understanding Proficient Historical data loads, ETL, data sync

Testing Strategy Strong Integration testing, mocks, test data management

Technical leadership

- System Design:
Architect end-to-end flows across agent, MCP, and external services

- Debugging Complex Issues:
Trace issues across multiple distributed services

- Code Review Excellence:
Enforce DRY, SOLID, error handling, observability standards

- Technical Decision Making:
Evaluate tradeoffs (batch vs sequential, caching, retries)

- Cross-Team Coordination:
Collaborate with Supplier Hub, SDE, Platform teams