About the Role
Frontier models are a commodity. The knowledge you feed them is not.
As a Staff AI Platform Engineer, you build the AI and data platform that powers Afresh's products: the knowledge and retrieval layer that makes grocery data reliably usable by LLMs, the agent systems built on top of it, and the evaluation and serving infrastructure underneath. Your "customers" are Afresh's own engineers and AI products — your job is to give them a platform that turns raw grocery data into context a model can be trusted with, at production quality.
This is senior, 0-to-1 platform work. You'll make foundational choices about how we represent grocery knowledge, ground our models, and measure whether any of it is actually working — in a fast-moving space with no playbook.
What You’ll Do
Build the knowledge & retrieval layer
- Design and operate the knowledge graph and ontology that capture how grocery data relates.
- Build the retrieval systems (vector, graph, and structured) that feed the right context to our models — so grounding is reliable, not lucky.
Build and serve the agent platform
- Build LLM-powered agents (tool-use, multi-step reasoning, orchestration) and the serving infrastructure to run them reliably and cost-effectively.
- Build the tools, abstractions, and interfaces other engineers depend on — a platform, not one-off features.
Own evaluation, quality, and the data foundation
- Stand up eval sets, LLM-as-judge harnesses, tracing, and observability, plus the metrics (faithfulness, accuracy, hallucination rate, latency, cost) that tell us whether a change helped or hurt.
- Build the pipelines, data products, and experimentation on Databricks/MLflow that take work from prototype to production — and partner with the engineers deploying our AI in the field to harden what works into reusable capabilities.
What Makes You a Good Fit
We encourage all highly-qualified candidates to apply, even if they do not fulfill all the listed criteria.
- 5+ years building production software, data, or ML systems; an excellent engineer with strong systems and API design (Python).
- Hands-on production experience with LLM systems: retrieval/RAG, agents and tool-use, prompt and context engineering — and, critically, evaluation. You measure quality; you don't eyeball it.
- Solid data-engineering and data-platform foundations: pipelines, data modeling, and a modern cloud data stack (Databricks/Spark, MLflow, cloud warehouses).
- Comfort in the messy middle of AI systems — retrieval quality, latency and cost trade-offs, non-determinism — and the instinct to build the guardrails and evals that make them trustworthy.
- A platform mindset: you build for leverage and clean interfaces, and you thrive in ambiguity in a fast-moving space.
Nice to Have
- Knowledge graphs, ontologies, or semantic layers in production; graph databases.
- Vector stores (pgvector, Pinecone, Weaviate, etc.) and hybrid search.
- MCP or similar tool/context protocols; agent frameworks (e.g., LangGraph).
- MLOps and model serving at scale; experimentation and observability tooling for LLM systems.
- Experience in grocery, retail, or other complex enterprise data domains.
Our Tech Stack
- Python, PySpark, dbt
- Databricks (Delta Lake, Unity Catalog, MLflow)
- Astronomer (Airflow) for orchestration
- LLMs and agents (Claude), retrieval over vector + graph stores, MCP tooling, eval and observability harnesses
- Claude, GitHub, Shortcut, Notion for development workflows
Why Afresh?
- We're a mission-driven company that eliminates hundreds of millions of pounds of food waste in grocery stores every year — your platform powers products with direct, visible impact.
- Build the foundation the rest of the product stands on: high-leverage, 0-to-1 work where your abstractions make the whole team faster.
- Be part of an engineering culture that's genuinely AI-forward — we want to be on the bleeding edge of agentic systems, not watching from the sidelines.
- Senior team, high trust, and real ownership at a pivotal inflection point for how Afresh scales.
- Collaborative, supportive environment & awesome people :)
This is a hybrid role based in the San Francisco office (2 days/week)
This position is not eligible for company sponsorship.
Salary Band in U.S. (USD): $168,912-$273,368
