Staff AI Platform Engineer – End-to-End LLM Platform

Fanatics Inc.; San Francisco (CA); On-site; USD 190,000 - 280,000; Full time

Job summary

Fanatics Commerce in Redwood City, CA, is seeking a Staff Software Engineer for its AI/ML Platform team. You will own the architecture of the AI control plane, including gateway, runtime, registry, retrieval, and evaluation components, and drive cost governance across the platform.

The role demands hands-on work with enterprise-grade tooling, multi-provider LLM routing, and scalable data pipelines, partnering with data scientists and engineers to deliver a robust, self-hosted path when needed.

Qualifications

• 8+ years building production software, including 2+ years on AI/ML platform.
• Staff-level impact: design across services and platforms used by other engineers.
• Strong Python and FastAPI, plus one of Java/Go/Scala/TypeScript; hands-on with Terraform, Kubernetes, Airflow, Postgres, Grafana, Prometheus; familiar with PyTorch.

Responsibilities

• Own the end-to-end architecture of the AI control plane: gateway, agent runtime, registry, retrieval, evaluation, and cost.
• Build the enterprise LLM gateway: multi-provider routing, failover, caching, rate limiting, and data residency considerations.
• Build the Agent/MCP ecosystem on a managed runtime (e.g., AWS BedrockAgentCore) with governed tools and no-code paths to production.
• Own the unified retrieval layer and data platform: ingestion, embedding, indexing, and vector/search backends at scale.
• Develop the evaluation and feedback loop: offline evals, tracing, regression gates in CI/CD, and root-cause attribution across prompts, retrieval, tools, and models.
• Own governance and cost: RBAC, audit logging, and enterprise AI tool portfolio oversight; interface with finance and legal teams.
• Raise the bar: set engineering standards, mentor engineers, and present trade-offs to senior leadership.

Skills

Python

FastAPI

Java

Go

TypeScript

Terraform

Kubernetes

Airflow

Postgres

Grafana

Prometheus

PyTorch

Education

Bachelor's or Master's in CS/Engineering

Tools

Bedrock

Vertex

AWS Bedrock AgentCore

Job description

Fanatics Commerce in Redwood City, CA, is seeking a Staff Software Engineer for its AI/ML Platform team. You will own the architecture of the AI control plane, including gateway, runtime, registry, retrieval, and evaluation components, and drive cost governance across the platform.

The role demands hands-on work with enterprise-grade tooling, multi-provider LLM routing, and scalable data pipelines, partnering with data scientists and engineers to deliver a robust, self-hosted path when needed.