Applied Research Engineer at Sully.ai

At Sully.ai , We’re Building the Most Impactful Healthcare Company on Earth We believe that access to a great doctor is a basic human right. Today, that’s not a reality. Delays, misdiagnoses, administrative chaos, and burnout plague the system. One Human, One Doctor . We build AI teammates that augment clinicians — scribes, nurses, receptionists, translators — all powered by our own world-class models and deployed in real-world care. 450+ organizations signed 16 months AI agents cut admin by ~2.8 hours daily and reduce onboarding 85%. 5M+ Clinical Tasks completed to date, serving 36+ specialties. Raised $25M from YC, Eric Yuan, Amity, Semper Virens Patented AI architecture (MedCon-1) outperforms GPT-4.5, Gemini, Claude on clinical reasoning tasks Sully requires A-players capable of 4 months = 1 year output. Build and scale automated evaluation pipelines (LLM-as-judge + human review) with clinical-grade benchmarks. Proven experience designing agentic processes and LLM evaluation/benchmarking frameworks. Strong Python and ML background (PyTorch/TensorFlow, Hugging Face, LangChain/LlamaIndex). Demonstrated ability to design rigorous experiments and translate findings into production.