Senior AI Engineer, Production LLM Systems
AI-native healthcare technology startup, remote
About the role
AI is the core product here, not an add-on. The platform is customer-facing and production-critical, so accuracy, reliability, explainability, and performance all matter. This is a hands-on role for someone who has personally owned AI architecture decisions, deployed into production, then improved latency, retrieval quality, hallucination rates, and monitoring after launch. Builders, not researchers.
What you will own
- Production LLM applications, RAG, and multi-agent or agentic systems from architecture through long-term operation.
- Evaluation frameworks, hallucination reduction, drift detection, and AI observability.
- Backend AI engineering in Python on AWS: FastAPI, event-driven architecture, vector databases.
- Document understanding and extraction across unstructured clinical and financial documents.
What we are looking for
- Has shipped customer-facing production AI systems, not internal experiments.
- Knows when to prompt, retrieve, fine-tune, or go agentic, and can explain the tradeoffs in latency, accuracy, cost, and maintainability.
- Strong Python and backend API development, plus LangChain, LangGraph, LlamaIndex, or similar in production.
- Thrives in a startup: finds problems before they are assigned, works with minimal direction.
Nice to have
- Healthcare: RCM, medical coding, clinical documentation, claims, HIPAA, EHR/FHIR/HL7.
- Fine-tuning experience (LoRA, QLoRA) and OCR or large-scale document pipelines.
What working with Satoriq is like on this search
We run searches like this regularly. Apply and we will screen you live, tell you honestly where you stand, and bring you to the right client the moment the seat is open.
Similar roles
Forward Deployed Engineer
Venture-backed applied AI company, early stage, NYC
Senior Software Engineer, Backend
Series A AI-native healthcare tech, NYC
Smart Contract Engineer, DeFi Protocols
Enterprise onchain finance infrastructure, NYC