AI Agent Engineer - US Remote at TRM Labs

<h2>Build a Safer World.</h2><p style="min-height:1.5em">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.</p><p style="min-height:1.5em">The AI Engineering Team is chartered with enabling <strong>next-generation AI applications</strong>, with a special focus on <strong>Large Language Models (LLMs)</strong> and <strong>agentic systems</strong>. Our mission is to build robust pipelines, high-performance infrastructure, and operational tooling that allow AI systems to be deployed with <strong>speed, safety, and scale</strong>.</p><p style="min-height:1.5em">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 <strong>evaluating and integrating cutting-edge tools in the LLM and agent space</strong> — including open-source stacks, vector databases, evaluation frameworks, and orchestration tools that unlock TRM’s ability to innovate faster than the market.</p><p style="min-height:1.5em"><strong>The impact you will have:</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Architect and implement a robust agentic framework that supports tool use, context retrieval, memory, and planning</p></li><li><p style="min-height:1.5em">Build intelligent, modular agents that automate investigative tasks and augment analyst decision-making</p></li><li><p style="min-height:1.5em">Extend and scale our LLM infrastructure (e.g. OpenAI, Anthropic, local models), including prompt engineering, RAG, and evaluation loops</p></li><li><p style="min-height:1.5em">Design safe, observable, and auditable agent behaviors — ensuring reliability in high-sensitivity environments</p></li><li><p style="min-height:1.5em">Evaluate performance across metrics like reasoning, latency, success rate, and hallucination, and iterate based on user feedback and system telemetry</p></li><li><p style="min-height:1.5em">Contribute to a culture of high ownership, rapid experimentation, and ethical AI deployment</p></li></ul><p style="min-height:1.5em"><strong>What we’re looking for:</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Strong engineering background with deep experience in backend or systems work (Python preferred)</p></li><li><p style="min-height:1.5em">Hands-on experience building with LLMs, agents, and tooling frameworks (LangChain, semantic caches, vector DBs, etc.)</p></li><li><p style="min-height:1.5em">Comfort working with agentic pipelines and optimizing information flow into AI systems</p></li><li><p style="min-height:1.5em">Thoughtful approach to system design, with an eye for safety, scalability, and e