AI Agent Engineer - San Francisco Only

TRM Labs; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

TRM Labs in San Francisco is seeking to advance AI engineering with a focus on large language models and agentic systems. This team builds robust pipelines, high-performance infrastructure, and tooling to deploy AI at speed, Safety, and scale for investigations and risk management.

You will architect an intelligent agent framework, develop modular agents to assist investigators, and extend the LLM stack with prompt engineering, retrieval, and evaluation loops.

Responsibilities

• Architect and implement a robust agentic framework that supports tool use, context retrieval, memory, and planning
• Build intelligent, modular agents that automate investigative tasks and augment analyst decision-making
• Extend and scale our LLM infrastructure (e.g. OpenAI, Anthropic, local models), including prompt engineering, RAG, and evaluation loops
• Design safe, observable, and auditable agent behaviors — ensuring reliability in high-sensitivity environments

Job description

Build a Safer World.

TRM Labs provides AI-powered intelligence solutions that help public and private sector agencies investigate and disrupt crime. TRM's platforms enable investigators to trace illicit activity, build cases, and construct operating pictures of threat networks. Leading agencies and businesses worldwide rely on TRM to make the world safer and more secure.

The AI Engineering Team is chartered with enabling next-generation AI applications, with a special focus on Large Language Models (LLMs) and agentic systems. Our mission is to build robust pipelines, high-performance infrastructure, and operational tooling that allow AI systems to be deployed with speed, safety, and scale.

We manage petabyte-scale pipelines, serve models with millisecond-level latency, and provide the observability and governance needed to make AI production-ready. We’re also deeply involved in evaluating and integrating cutting-edge tools in the LLM and agent space — including open-source stacks, vector databases, evaluation frameworks, and orchestration tools that unlock TRM’s ability to innovate faster than the market.

The impact you will have:

• Architect and implement a robust agentic framework that supports tool use, context retrieval, memory, and planning

• Build intelligent, modular agents that automate investigative tasks and augment analyst decision-making

• Extend and scale our LLM infrastructure (e.g. OpenAI, Anthropic, local models), including prompt engineering, RAG, and evaluation loops

• Design safe, observable, and auditable agent behaviors — ensuring reliability in high-sensitivity environments