Staff Research Engineer
Core
Building decision-making systems for AI agents operating across voice, chat, and email, focusing on reliability in real-world customer environments.
Role type
Staff Research Engineer (Applied AI/LLM Systems)
Builds
Production-ready reasoning systems, memory/retrieval architectures, and multi-step agent workflows for voice, chat, and email channels.
Domain
Artificial Intelligence, Large Language Models (LLM), Agent-based Systems
Deliverable
production ML models
Required skills
LLM production experience, Reinforcement Learning (RL), post-training techniques, agent-based system design, memory and retrieval architecture, multi-step workflow execution, tool use integration, end-to-end system engineering, real-world model behavior analysis
Preferred skills
Experience with long-context interactions, system reliability under real-world constraints, cross-functional collaboration with product teams
Technologies
LLMs, RL frameworks, agent orchestration tools, production deployment pipelines
Responsibilities
Design and improve reasoning systems for real-world agent workflows; Build and refine memory, retrieval, and multi-step execution systems; Develop post-training and evaluation approaches for deployed models; Iterate on systems based on real user behavior and performance; Take research ideas through to production environments
Seniority
Staff, high autonomy & strategic ownership
