About the Role
Join a small, fast-moving team building AI software for public safety and criminal justice workflows. You will design and deploy secure systems that help investigators search and analyze complex evidence, contributing directly to high-stakes real-world work.
What You'll Do
Build resilient, secure distributed systems for AI-powered evidence search and analysis.
Deploy large language models, vision models, and other machine learning systems in production environments.
Design retrieval-augmented generation pipelines and semantic search for unstructured evidence.
Build structured data systems with query planning, semantic modeling, or reasoning capabilities.
Develop or integrate agentic systems that can reason, plan, and take actions across investigative data.
Evaluate emerging AI models and infrastructure approaches, and drive solutions from discovery through deployment.
What We're Looking For
At least 6 years of backend engineering experience building distributed systems, including production deployment of LLMs, vision models, or other machine learning systems.
Strong experience with Python and multiple programming languages, potentially including JavaScript and React.
Hands-on experience with RAG or similar pipelines for unstructured data, and systems for structured data such as query planning or semantic reasoning.
Experience working across multiple infrastructure providers and building for security and resilience.
A track record spanning established technical environments and early-stage startups, plus comfort with ambiguity and rapid iteration.
Experience with agentic AI is a plus. Must already be authorized to work in the United States; visa sponsorship is not available.
Compensation & Benefits
Base salary is $150,000 to $215,000 annually. Visa sponsorship is not available.
Location
Hybrid in San Francisco, California, United States.