AI Engineer: Agentic Systems & LLM Infra

Aimlroles; Northern (KY); Hybrid; USD 200,000 - 250,000; Full time

Job summary

TRM Labs seeks an AI Engineer to build robust agentic systems operating with safety, speed, and scale. You will extend LLM infrastructure, integrate tools, and optimize data flows for real-world investigative tasks.

You will work on backend systems with Python, leverage LangChain and vector databases, and design auditable agent behaviors in high-sensitivity environments. The role emphasizes collaboration and rapid experimentation.

Qualifications

• Strong engineering background in backend or systems work, Python preferred.
• Hands-on experience building with LLMs and tooling frameworks (LangChain, vector databases, semantic caches).
• Comfort 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 end users.

Responsibilities

• Architect and implement a robust agentic framework for tool use, memory, and planning.
• Build intelligent agents to automate investigative tasks and augment analysts.
• Scale LLM infrastructure including prompt engineering, RAG, and evaluation loops.
• Design safe, observable, auditable agent behaviors for high-sensitivity environments.
• Evaluate performance metrics and iterate based on telemetry and user feedback.

Skills

Backend systems

LLM & agents

Python

LangChain

Vector databases

System design

Experimentation

AI safety

Tools

LangChain

Semantic caches

Vector DBs

Job description

TRM Labs seeks an AI Engineer to build robust agentic systems operating with safety, speed, and scale. You will extend LLM infrastructure, integrate tools, and optimize data flows for real-world investigative tasks.

You will work on backend systems with Python, leverage LangChain and vector databases, and design auditable agent behaviors in high-sensitivity environments. The role emphasizes collaboration and rapid experimentation.