Agent Engineer
Design and implement agentic frameworks supporting tool use, context retrieval, memory, and planning. Build modular agents for investigative automation, scale LLM infrastructure, develop prompt engineering and RAG pipelines, and create safe, observable, auditable AI behaviors.
Responsibilities
- Architect and implement agentic frameworks for tool use, retrieval, memory, and planning
- Build modular agents that automate investigative tasks and support analyst decision-making
- Extend and scale LLM infrastructure, including prompt engineering, RAG, and evaluation loops
- Design safe, observable, and auditable agent behaviors
- Evaluate reasoning, latency, success rate, and hallucination metrics
- Iterate based on user feedback and system telemetry
- Deliver production-ready AI systems through rapid experimentation
Requirements
- Strong engineering background with deep backend or systems experience
- Experience building with LLMs, agents, LangChain, semantic caches, and vector databases
- Comfort with agentic pipelines and optimizing information flow into AI systems
- Strong system design skills with attention to safety, scalability, and explainability
- High product empathy and concern for end-user impact
- Bias toward experimentation and rapid iteration
- Knowledge graphs, task orchestration, or AI safety experience is a plus
Benefits
- Eligibility to participate in TRM's equity plan