AI Research Engineer

About the role As an AI Engineer on our research team, you’ll work on our hardest research and AI infra problems. You’ll help prototype new products and turn prototypes into high‑quality AI products. Hard problems include passing the healthcare billing Turing Test— would an insurance agent interacting with our AI or a healthcare biller reviewing our AI’s work think the AI is a human? More concretely, you will improve our AI agent’s quality so it acts more human‑like and collects more accurate and detailed results from insurance. What you’ll do Main focus is on improving models, LLM orchestration, prompt optimizations, evaluation framework, and AI infra Enable agent/workflow product engineers Own and raise the bar on AI quality Own ultimate vision of end‑to‑end AI orchestration of modules Work on hardest research problems (e.g., Anti‑AI) Mainly a mix of ML, data science, and applied LLM work. Heavy Python. Who we’re looking for You like reading the latest LLM research papers Deep experience in implementing and building AI agents Eager to try out the latest releases (e.g., o1, OpenAI voice mode, Claude Computer‑Use) to see how it can be used in real‑world healthcare billing applications Worked with complex distributed systems with many async operations Excited about pushing the boundaries of conversational AI technology Can balance quick experimentation with systematic evaluation Very high Python mastery Perks & Benefits In‑person culture at our Flatiron office in NYC with paid lunch and dinner Flexible hours and time off Gym stipend Commuter benefits Health, dental, vision insurance 401(k) with matching contribution Annual offsite #J-18808-Ljbffr