AI Agent Engineer - US Remote

📋 Description

• Architect and implement an agentic framework with tool use, memory, and planning
• Build modular agents to automate investigative tasks and aid analysts
• Extend and scale LLM infrastructure, including prompt engineering, RAG, and evaluation loops
• Design safe, observable, auditable agent behaviors for high-sensitivity environments
• Evaluate metrics: reasoning, latency, success, and hallucination; iterate
• Contribute to a culture of ownership and rapid experimentation in AI deployment

🎯 Requirements

• Strong engineering background in backend or systems; Python preferred
• Hands-on with LLMs, agents, and tooling (LangChain, vector DBs, caches)
• Experience with agentic pipelines and optimizing AI information flow
• System design focus on safety, scalability, and explainability
• Product empathy for analysts; optimize agent impact
• Bias toward experimentation; eager to try, learn, and ship fast

🎁 Benefits

• Remote-friendly, distributed-first with global hubs
• Competitive base salary and equity plan
• Work on state-of-the-art AI and LLMs