Staff Software Engineer - AI/ML Platform
About this role
The AI/ML Platform pod at Fanatics Commerce constructs the internal AI platform that serves as the paved road for every team building with LLMs, MCPs, and agents. Operating across a petabyte-scale lakehouse with enterprise-grade governance, this pod manages the gateway, agent runtime, registry, retrieval, evaluation, and cost analytics end to end.
In this hands-on Staff Software Engineer capacity, the individual guides the architecture, defines the technical standards for other engineering teams, and writes code to ship the most complex system components. The position requires substantial background in building production software and AI/ML platforms, with the ability to navigate system design across multiple services and represent architectural trade-offs directly to senior leadership.
What you will do
- Own the end-to-end architecture of the AI control plane including the gateway, agent runtime, registry, retrieval, evaluation, and cost components.
- Build the enterprise LLM gateway with multi-provider routing, failover, caching, rate limiting, token optimization, and key management.
- Develop the Agent and MCP ecosystem on a managed runtime such as AWS BedrockAgentCore with governed tools and a control-plane registry.
- Manage the unified retrieval layer and data platform including ingestion, chunking, embedding, indexing pipelines, and vector backends.
- Construct the evaluation and feedback loop featuring offline evaluations, tracing, regression gates in CI/CD, and root-cause attribution.
- Handle governance and cost requirements such as RBAC, agent identity, least-privilege access, audit logging, and use-case cost attribution.
- Set engineering standards, mentor colleagues, and communicate architectural trade-offs to senior leadership.
What you need
- Over 8 years of experience building production software, including 2 or more years specifically focused on AI/ML platforms.
- Bachelor's or Master's degree in Computer Science, Engineering, a related field, or equivalent practical experience.
- Demonstrated Staff-level impact involving system design across multiple services and platforms utilized by other engineers.
- Strong proficiency in Python and FastAPI, alongside working knowledge of at least one language like Java, GoLang, Scala, or TypeScript.
- Hands-on operational experience with Terraform, Kubernetes, Airflow, Postgres, Grafana, and Prometheus.
- Familiarity with LLMs and generative AI on platforms like Bedrock or Vertex, covering model routing, RAG, and tool calling.
Nice to have
- Exposure to self-hosted model serving with vLLM, SGLang, or llama.cpp
- Experience with chat UI or internal developer portal development
- Familiarity with data governance systems like DataHub and semantic layers
- Experience administering enterprise AI tools such as ChatGPT Enterprise, Claude Enterprise, or Glean
- Open-source contributions or published work in agentic AI or LLMOps
Benefits
- For information about benefits, please visit https://benefitsatfanatics.com/
Skills and tech stack
Questions candidates ask
What is the salary range for this role?
The base salary range is $190,000 to $237,500 USD. The final compensation package is determined by factors such as location, experience, qualifications, and training.
What kind of systems will I be building?
You will build the internal AI platform that serves as the paved road for every team building with LLMs, MCPs, and agents. This includes the AI control plane, enterprise LLM gateway, Agent/MCP ecosystem, unified retrieval layer, and evaluation loops.
What technical background is required?
Candidates need over 8 years of production software building experience with 2+ years on AI/ML platforms. Strong proficiency in Python, FastAPI, and hands-on experience with Terraform, Kubernetes, Airflow, Postgres, Grafana, and Prometheus are required.
The application is on the official Fanatics Commerce careers page.
Apply on company site