Staff Frontier Agents Engineer (Applied AI)

Responsibilities: Design and deploy production AI agents leveraging LLMs, reasoning, retrieval, memory, and tools Architect systems combining LLMs, traditional ML, structured knowledge, and enterprise data Develop memory, retrieval, and knowledge representations for large heterogeneous datasets Build multi-agent systems coordinating reasoning, planning, tool use, and human oversight Translate frontier AI research into production via evaluation of models, prompts, and architectures Own end-to-end experimentation lifecycle from hypothesis to production rollout Design evaluation frameworks including offline benchmarks, online experiments, and human evaluation Develop confidence estimation, reflection, and continuous learning to improve agents over time Collaborate with infrastructure to deploy secure, reliable AI systems in enterprise cloud environments Create human-in-the-loop workflows integrating AI with expert oversight Partner with customers to understand business data and translate problems into architectures Prototype ideas, validate with customers, and scale successful solutions Identify reusable patterns to apply across deployments Measure business impact through real-world outcomes

Key requirements: 8+ years of software engineering, ML, or applied AI experience Strong Python programming skills Experience building production AI systems using LLMs Experience with modern AI tooling: OpenAI, Claude, MCP, agent frameworks, vector databases, or retrieval systems Strong understanding of ML fundamentals and modern language models Experience designing or evaluating AI systems using quantitative metrics Excellent communication skills and ability to work with enterprise customers excellent communication customer-facing collaboration work with cross-functional teams production AI systems LLMs retrieval systems