Staff Software Engineer, Agent AI Systems & Safety

TRM Labs; United States; On-site; USD 200,000 - 275,000; Full time

Benefits offered by this job

Equity plan

Job summary

TRM Labs is building a safer world with AI-powered intelligence solutions for investigative work. The AI Engineering team focuses on next-generation AI apps, LLMs, and agentic systems, delivering robust pipelines, high-performance infrastructure, and safe tooling.

We manage large-scale pipelines and latency-sensitive model serving, evaluating cutting-edge tools in LLM and agent spaces, aiming for speed, safety, and scale in production.

Qualifications

• Strong backend/systems experience (Python preferred).
• Hands-on with LLMs, agents, and tooling frameworks (LangChain).
• Comfort working with agentic pipelines and optimizing information flow into AI systems.
• Thoughtful system design with safety, scalability, and explainability in mind.
• High product empathy for analysts and users, with fast experimentation.

Responsibilities

• Architect and implement a robust agentic framework that supports tool use, context retrieval, memory, and planning
• Build intelligent, modular agents that automate investigative tasks and augment analyst decision-making
• Extend and scale our LLM infrastructure (e.g. OpenAI, Anthropic, local models), including prompt engineering, RAG, and evaluation loops
• Design safe, observable, and auditable agent behaviors — ensuring reliability in high-sensitivity environments
• Evaluate performance across metrics like reasoning, latency, success rate, and hallucination, and iterate based on user feedback and system telemetry
• Contribute to a culture of high ownership, rapid experimentation, and ethical AI deployment

Skills

Backend engineering

Python

LLMs

Agents

LangChain

Vector DBs

System design

Safety

Experimentation

Tools

OpenAI

Anthropic

Local models

RAG

Evaluation frameworks

Orchestration tools

Job description

TRM Labs is building a safer world with AI-powered intelligence solutions for investigative work. The AI Engineering team focuses on next-generation AI apps, LLMs, and agentic systems, delivering robust pipelines, high-performance infrastructure, and safe tooling.

We manage large-scale pipelines and latency-sensitive model serving, evaluating cutting-edge tools in LLM and agent spaces, aiming for speed, safety, and scale in production.