10 months ago
Base Salary
$200k - $275k/yr
Responsibilities
- Architect and implement an agentic framework supporting tool use, context retrieval, memory, and planning.
- Build modular intelligent agents that automate investigative tasks and augment analyst decision-making.
- Extend and scale LLM infrastructure, including prompt engineering, RAG, and evaluation loops.
- Design safe, observable, auditable, reliable, and explainable agent behaviors for high-sensitivity environments.
- Evaluate reasoning, latency, success rate, and hallucination metrics, then iterate using user feedback and system telemetry.
- Contribute to rapid experimentation, operational excellence, documentation, knowledge sharing, and ethical AI deployment.
Requirements
- Strong software engineering background with deep backend or systems experience; Python is preferred.
- Hands-on experience building with LLMs, agents, and tooling frameworks such as LangChain, semantic caches, and vector databases.
- Comfort working with agentic pipelines and optimizing information flow into AI systems.
- Strong system design judgment focused on safety, scalability, and explainability.
- Product empathy and ability to optimize agent behavior for real analyst users.
- Bias toward experimentation, iteration, and rapid delivery.
- Experience with knowledge graphs, task orchestration, or AI safety is a plus.
- Strong communication, leadership, teamwork, and collaboration skills.
Benefits
- US-remote role within a distributed-first company with hubs in Los Angeles, San Francisco, New York, Washington, D.C., London, and Singapore.
- May be eligible to participate in TRM’s equity plan.
- Inclusive, collaborative, high-ownership environment focused on meaningful work at the intersection of AI, national security, and fighting crime.
Tech Stack
Categories
About TRM Labs
TRM Labs builds AI-powered blockchain intelligence and investigation software for government agencies and financial institutions to detect, trace, and disrupt crypto‑related crime. Its platform supports AML, sanctions, fraud, and threat‑intelligence use cases, combining data analytics with tools for case building and transaction monitoring. Founded in 2018 and headquartered in San Francisco, the privately held company serves customers worldwide across public‑ and private‑sector markets.