AI Agent Engineer (Remote)

TRM Labs is looking for an AI Agent Engineer to build agentic systems that augment investigative workflows and help public/private agencies disrupt crime. In this role, you'll architect agent frameworks, integrate LLM infrastructure, and design safe, auditable AI behaviors.

• Architect and implement a robust agentic framework supporting tool use, context retrieval, memory, and planning
• Build intelligent, modular agents that automate investigative tasks and augment analyst decision-making
• Extend and scale LLM infrastructure (OpenAI, Anthropic, local models) including prompt engineering, RAG, and evaluation loops
• Design safe, observable, and auditable agent behaviors for high-sensitivity environments
• Evaluate agent performance across reasoning, latency, success rate, and hallucination; iterate based on feedback and telemetry

• Strong engineering background with deep backend or systems experience (Python preferred)
• Hands-on experience with LLMs, agents, and tooling frameworks such as LangChain, semantic caches, and vector DBs
• Comfortable with agentic pipelines and optimizing information flow into AI systems
• Thoughtful system design with attention to safety, scalability, and explainability
• High product empathy and bias toward experimentation and iteration