Staff Software Engineer, Agent Engineering
Architect and implement agentic frameworks supporting tool use, context retrieval, memory, and planning. Build modular agents for investigative tasks, extend LLM infrastructure, develop prompt engineering and RAG workflows, design safe and auditable agent behaviors, and evaluate system performance using feedback and telemetry.
Responsibilities
- Architect and implement a robust agentic framework supporting tool use, context retrieval, memory, and planning
- Build intelligent, modular agents that automate investigative tasks and augment analyst decision-making
- Extend and scale LLM infrastructure, including prompt engineering, RAG, and evaluation loops
- Design safe, observable, and auditable agent behaviors for reliable operation in high-sensitivity environments
- Evaluate reasoning, latency, success rate, and hallucination performance and iterate using user feedback and telemetry
- Contribute to high ownership, rapid experimentation, and ethical AI deployment
Requirements
- Strong engineering background with deep backend or systems experience; Python preferred
- Hands-on experience building with LLMs, agents, and tooling frameworks such as LangChain, semantic caches, and vector databases
- Experience with agentic pipelines and optimizing information flow into AI systems
- Thoughtful system design with attention to safety, scalability, and explainability
- High product empathy and ability to optimize agent behavior for real users
- Bias toward experimentation and iteration
- Knowledge graphs, task orchestration, or AI safety experience is a plus
Benefits
- Eligibility to participate in TRM’s equity plan