Staff Software Engineer, Agent Engineering

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

📋 Description

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

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

• Expand and optimize our LLM infrastructure (including OpenAI, Anthropic, and local models), focusing on prompt engineering, RAG, and evaluation loops.

• Create safe, observable, and auditable agent behaviors to ensure dependability in high-sensitivity environments.

• Assess performance based on metrics such as reasoning, latency, success rate, and hallucination, and refine processes using user feedback and system telemetry.

• Foster a culture of high ownership, rapid experimentation, and ethical AI implementation.

⛳️ Requirements

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

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

• Comfort with agentic pipelines and optimizing the flow of information into AI systems.

• A thoughtful approach to system design, prioritizing safety, scalability, and explainability.

• High product empathy—genuinely care about how agents influence real users (analysts) and optimize accordingly.

• A bias towards experimentation and iteration—enthusiastic about trying new things, learning, and delivering quickly.

• Prior experience with knowledge graphs, task orchestration, or AI safety is a plus.

🏝️ Benefits

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