Overview:
In this role you design, build, and operate production AI systems at scale to transform clinical documents into actionable data. You will own end-to-end solutions spanning frontend, APIs, model orchestration, and data pipelines within one of the largest U.S. health insurers. You’ll tackle accuracy, explainability, traceability, and reliability in a regulated healthcare environment. This is a hands-on, impact-driven position that ships in a small, high-impact team. Compensation / Benefits medical, dental, and vision benefits 401(k) retirement savings plan paid time off and holidays paid parental and caregiver leave short-term and long-term disability life insurance
Responsibilities:
Design, develop, and deploy full-stack AI-powered applications (frontend, APIs, backend, data pipelines) Create and optimize LLM-based workflows for extraction, classification, retrieval, summarization, and agentic processes Develop robust prompts, structured outputs, tool-calling, and fallback mechanisms Design retrieval-augmented generation (RAG) systems using embeddings, vector databases, and semantic search Build evaluation frameworks with benchmarks, regression tests, quality metrics, and human review workflows Develop human-in-the-loop processes for clinician/experts feedback and validation Create document-processing pipelines (OCR, ingestion, metadata extraction, indexing, search) Optimize systems for accuracy, latency, reliability, scalability, and cost Implement observability, monitoring, logging, alerting, and incident response for production systems Deploy and operate in cloud-native environments (Kubernetes, Docker, CI/CD, modern tooling) Collaborate with product, engineering, clinical, and operations to translate requirements into scalable solutions Ensure privacy, security, compliance, and auditability in a regulated healthcare environment
Key requirements:
Bachelor’s degree in Computer Science, Engineering, or related field, or equivalent practical experience 5+ years building and operating production software systems Experience developing backend services, APIs, distributed systems, or data-intensive applications Hands-on experience integrating LLMs into production apps with structured outputs, tool calling, RAG, agents, or multi-step workflows Experience with at least one major AI platform or model provider (OpenAI, Anthropic, Google, Azure AI, AWS Bedrock) Strong programming skills in Python and/or TypeScript/JavaScript Experience debugging, monitoring, and supporting production applications for real customers Ability to work independently, navigate ambiguity, and own projects end-to-end Strong problem-solving Clear communication Collaboration TypeScript React/Next.js Python