About the Role Join a small, early-stage public safety technology team building AI-powered tools for law enforcement. You will design and deploy secure, real-world systems that help investigators search and analyze evidence for serious cases. What You'll Do • Build resilient, secure distributed systems for AI-driven evidence search and analysis. • Deploy large language models, vision models, and other machine learning systems in production. • Design retrieval-augmented generation pipelines and semantic search 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 own solutions from discovery through deployment. What We're Looking For • At least 6 years of backend engineering experience building distributed systems, with production deployment experience for LLMs, vision models, or other ML systems. • Proficiency across multiple programming languages, including Python, and experience with JavaScript or React. • Experience building secure, resilient systems and working across multiple infrastructure providers. • Hands-on experience with RAG or similar pipelines for unstructured data, and structured data systems involving query planning, semantic modeling, or reasoning. • Experience in both established engineering environments and early-stage startups is valued. • Agentic AI experience is a plus. Applicants must be authorized to work in the United States; visa sponsorship is not available. Compensation & Benefits Base salary: $150,000 to $215,000 annually. Equity details were not provided. Location Hybrid role based in San Francisco, California.