2 months ago
Base Salary
$156k - $231k/yr
Responsibilities
- Design and operate the knowledge graph and ontology representing grocery-data relationships.
- Build vector, graph, and structured retrieval systems that provide reliable context to models.
- Build LLM-powered agents with tool use, multi-step reasoning, and orchestration.
- Develop reliable and cost-effective agent serving infrastructure, tools, abstractions, and interfaces for other engineers.
- Create evaluation sets, LLM-as-judge harnesses, tracing, observability, and metrics for faithfulness, accuracy, hallucination rate, latency, and cost.
- Build pipelines, data products, and experimentation workflows using Databricks and MLflow to take AI work from prototype to production.
- Partner with field AI engineers to harden successful systems into reusable platform capabilities.
Requirements
- At least 3 years of experience building production software, data, or ML systems.
- Strong Python engineering and systems and API design skills.
- Hands-on production experience with LLM retrieval/RAG, agents, tool use, prompt and context engineering, and evaluation.
- Solid data-engineering and data-platform foundations, including pipelines, data modeling, and a modern cloud data stack.
- Ability to manage retrieval quality, latency, cost, and non-determinism while building trustworthy guardrails and evaluations.
- Experience building for platform leverage, clean interfaces, and ambiguous, fast-moving environments.
- Preferred experience includes production knowledge graphs, ontologies, semantic layers, graph databases, vector stores, hybrid search, MCP or similar protocols, LangGraph or comparable agent frameworks, MLOps, model serving, experimentation, observability tooling, and grocery, retail, or other complex enterprise data domains.
Benefits
- Hybrid role based in the San Francisco office two days per week.
- Comprehensive medical, dental, and vision coverage with most premiums covered, plus mental health support and counseling.
- Meaningful equity for U.S. employees and a 401(k) program with company match.
- Home office stipend and Coworking Wallets for flexible workspace access.
- Annual professional development budget.
- Monthly Betterment and telecommunications stipends.
- Flexible paid time off.
Tech Stack
Categories
About Afresh
Afresh is the AI platform for Grocery — built for how grocery actually operates, from the fresh perimeter to center store and retail to distribution centers. The Afresh platform helps grocers make smarter decisions about what to buy, order, produce, and sell across the entire operation, delivering higher profits, less waste, and fresher food on the shelf. Founded in 2017 with the mission to eliminate food waste and make fresh food accessible to all, Afresh today supports more than 12,500 departments across 40 states, partnering with Albertsons Companies, Stater Bros., Meijer, Wakefern, and more. Learn more at www.afresh.com.