AI Agent Engineer: Build Safe, Scalable Agent Systems

Crypto Pro Network; San Francisco (CA); Remote; USD 215,000 - 230,000; Full time

Benefits offered by this job

Equity plan

Job summary

TRM Labs is seeking a senior engineer to join the AI Engineering team, focusing on building robust agentic systems and scalable AI tools. You will work on backend infrastructure, LLM-driven agents, and tooling to deploy safe, fast AI applications at scale.

You will shape the design of agentic pipelines, collaborate across time zones, and help protect users by advancing the state of responsible AI deployment. Equity may be part of the compensation, reflecting the high impact of this role.

Qualifications

• Strong backend or systems engineering experience, Python preferred.
• Hands-on experience building with LLMs, agents, and tooling frameworks (LangChain, vector caches, vector DBs).
• Comfort working with agentic pipelines and optimizing information flow into AI systems.
• Thoughtful approach to system design with emphasis on safety, scalability, and explainability.

Responsibilities

• Architect and implement a robust agentic framework supporting tool use, context retrieval, memory, and planning.
• Build intelligent modular agents to automate investigations and augment analyst decisions.
• Extend and scale LLM infrastructure (OpenAI, Anthropic, local models) including prompt engineering, RAG, and evaluation loops.
• Design safe, observable, auditable agent behaviors ensuring reliability in high-sensitivity environments.
• Evaluate performance across metrics like reasoning, latency, success rate, and hallucination; iterate from telemetry and feedback.
• Contribute to a culture of ownership, rapid experimentation, and ethical AI deployment.

Skills

Python

LLMs

Agents

LangChain

Vector databases

Tools

LangChain

Vector databases

Job description

TRM Labs is seeking a senior engineer to join the AI Engineering team, focusing on building robust agentic systems and scalable AI tools. You will work on backend infrastructure, LLM-driven agents, and tooling to deploy safe, fast AI applications at scale.

You will shape the design of agentic pipelines, collaborate across time zones, and help protect users by advancing the state of responsible AI deployment. Equity may be part of the compensation, reflecting the high impact of this role.