Staff Agent Engineer - US Remote
$200k - $275k • Remote • United States • FullTime
Posted 7mo ago
Job Location
United States
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Agent Engineer
About the job
TRM Labs is seeking a Staff Agent Engineer to join their AI Engineering Team, focusing on next-generation AI applications, particularly Large Language Models (LLMs) and agentic systems. The team's mission is to build robust pipelines, high-performance infrastructure, and operational tooling for the rapid, safe, and scalable deployment of AI systems. This role involves managing large-scale data pipelines, serving models with low latency, and ensuring AI systems are production-ready through observability and governance. The engineer will also evaluate and integrate cutting-edge tools in the LLM and agent space, including open-source stacks, vector databases, evaluation frameworks, and orchestration tools to accelerate innovation.
Responsibilities
- Architect and implement a robust agentic framework supporting tool use, context retrieval, memory, and planning.
- Build intelligent, modular agents to automate investigative tasks and augment analyst decision-making.
- Extend and scale LLM infrastructure, including prompt engineering, RAG, and evaluation loops.
- Design safe, observable, and auditable agent behaviors for reliability in high-sensitivity environments.
- Evaluate agent performance across metrics like reasoning, latency, success rate, and hallucination, iterating based on feedback and telemetry.
- Contribute to a culture of high ownership, rapid experimentation, and ethical AI deployment.
Requirements
- Strong engineering background with deep experience in backend or systems work (Python preferred).
- Hands-on experience building with LLMs, agents, and tooling frameworks (e.g., LangChain, semantic caches, vector DBs).
- Comfort working with agentic pipelines and optimizing information flow into AI systems.
- Thoughtful approach to system design, emphasizing safety, scalability, and explainability.
- High product empathy, focusing on how agents impact real users (analysts).
- Bias toward experimentation and iteration, with a desire to learn and ship fast.
- Previous experience with knowledge graphs, task orchestration, or AI safety is a plus.
Benefits
- Equity plan participation
- Potential for rapid issue resolution and efficient knowledge transfer