8 months ago
Base Salary
$200k - $275k/yr
Responsibilities
- Architect and implement an agentic framework supporting tool use, context retrieval, memory, and planning.
- Build modular AI agents that automate investigative tasks and augment analyst decision-making.
- Extend and scale LLM infrastructure using providers such as OpenAI, Anthropic, and local models.
- Develop prompt-engineering, RAG, and evaluation loops for AI systems.
- Design safe, observable, auditable, reliable, and explainable agent behaviors.
- Evaluate reasoning, latency, success rate, and hallucination performance and iterate using user feedback and telemetry.
- Contribute to rapid experimentation, operational excellence, ethical AI deployment, documentation, and knowledge sharing.
Requirements
- Strong engineering background with deep backend or systems experience, with Python preferred.
- Hands-on experience building with LLMs, agents, and tooling frameworks such as LangChain, semantic caches, and vector databases.
- Experience working with agentic pipelines and optimizing information flow into AI systems.
- Strong system-design judgment focused on safety, scalability, and explainability.
- Product empathy and interest in optimizing agent experiences for analyst users.
- A willingness to experiment, iterate, learn, and ship quickly.
- Experience with knowledge graphs, task orchestration, or AI safety is a plus.
- Strong communication, leadership, teamwork, and collaboration skills.
Benefits
- US-remote position at a distributed-first company with hubs in Los Angeles, San Francisco, New York, Washington D.C., London, and Singapore.
- Fast-paced, high-ownership environment with meaningful work at the intersection of AI, national security, and fighting crime.
- Eligible roles may participate in TRM's equity plan.
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.