Agent Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and implement a comprehensive agentic framework that facilitates tool utilization, context retrieval, memory management, and planning.

• Create intelligent, modular agents that streamline investigative tasks and enhance decision-making for analysts.

• Expand and enhance our LLM infrastructure (e.g., OpenAI, Anthropic, local models), which includes prompt engineering, retrieval-augmented generation (RAG), and evaluation loops.

• Develop safe, observable, and auditable agent behaviors to ensure reliability in sensitive environments.

• Assess performance using metrics such as reasoning, latency, success rates, and hallucination, and make iterative improvements based on user feedback and system telemetry.

• Foster a culture characterized by high ownership, rapid experimentation, and the ethical deployment of AI.

⛳️ Requirements

• Strong engineering foundation with extensive experience in backend or systems development (Python preferred).

• Practical experience in building with LLMs, agents, and tooling frameworks (LangChain, semantic caches, vector databases, etc.).

• Ability to work comfortably with agentic pipelines and optimize the flow of information into AI systems.

• Thoughtful system design approach, focusing on safety, scalability, and explainability.

• High product empathy; you care about the impact of agents on real users (analysts) and optimize accordingly.

• A tendency towards experimentation and iteration; you are eager to try, learn, and deliver quickly.

• Previous experience with knowledge graphs, task orchestration, or AI safety is an advantage.

🏝️ Benefits

• Additionally, this role may be eligible to participate in TRM’s equity plan.

• Health insurance.

• Wellness programs.

• Paid time off.