About the Role
Join a small engineering team building AI-powered software for law enforcement and other high-stakes public safety work. You will design and deploy systems that help investigators search and analyze complex evidence, contributing directly to tools used in serious investigations.
What You'll Do
Build resilient, secure distributed systems that support AI-driven 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 infrastructure for unstructured evidence.
Architect structured data systems, including query planning and semantic reasoning layers.
Build or work with agentic systems that reason, plan, and take actions across investigative data.
Evaluate emerging AI models and infrastructure approaches, and drive solutions from idea 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.
Proficiency in multiple programming languages, including Python, and experience with JavaScript and React.
Experience building secure, resilient systems across multiple infrastructure providers.
Hands-on experience with RAG or similar pipelines for unstructured data, plus structured data systems involving query planning, semantic modeling, or reasoning.
Experience with established technical organizations and early-stage startups is valued, along with a history of sustained contributions in roles.
Agentic AI experience and interest in public safety technology are helpful.
Must be authorized to work in the United States.
Compensation & Benefits
Salary range: $150,000 to $215,000 annually. Visa sponsorship is not available.
Location
Hybrid work arrangement in San Francisco, California.