Job Description
📋 Description Architect and implement a robust agentic framework with tool use, context, 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 high-sensitivity environments Evaluate metrics such as reasoning, latency, and hallucination; iterate from feedback and telemetry Contribute to a culture of ownership, rapid experimentation, and ethical AI deployment 🎯 Requirements Strong engineering background with backend or systems focus (Python preferred) Hands-on experience with LLMs, agents, and tooling (LangChain, semantic caches, vector DBs) Experience with agentic pipelines and optimizing AI information flow System design with safety, scalability, and explainability High product empathy; optimize agents for real analysts Bias toward experimentation and fast iteration Experience with knowledge graphs, task orchestration, or AI safety is a plus 🎁 Benefits Mission-driven work at the intersection of AI, safety, and national security Work in a distributed-first company with hubs in multiple cities High ownership culture with rapid experimentation and impact Collaborate across diverse teams with leadership and mentorship Exposure to cutting-edge AI tools, LLMs, and agent technology Eligible for equity plan
