Generative AI Engineer (LLMs & RAG) – Healthcare SaaS Location : Remote / Hyderabad (preferred) Experience : 5+ years Employment Type : Full-time Domain : Generative AI, Healthcare, SaaS About the Role We are looking for a hands-on Generative AI Engineer with expertise in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). In this role, you will architect and deliver production-grade AI systems that combine unstructured and structured healthcare data to power a next-generation clinical assistant. You will work at the cutting edge of Generative AI and healthcare innovation, helping design safe, scalable, and impactful solutions that directly influence real-world patient outcomes. This is a chance to take ownership of core AI systems in a fast-moving, high-impact product. Key Responsibilities - Architect and optimize RAG pipelines – ingestion, embedding, retrieval, grounding, and generation.
- Experiment with LLMs – open-weight models (LLaMA, Mistral, Falcon) and API-based models (OpenAI, Anthropic).
- Implement evaluation & monitoring frameworks (retrieval precision, grounding accuracy, hallucination checks, latency, safety).
- Work with diverse healthcare datasets – PDFs, EHR / EMR data, CSVs, structured knowledge bases.
- Deploy AI services to cloud-native environments (AWS, GCP, or Azure) with observability and security in mind.
- Collaborate cross-functionally with product, clinicians, DevOps, and QA to ship production-ready features. Must-Have Skills - 5+ years of experience in software / ML engineering with strong Python skills (backend + API development).
- Proven expertise building LLM-powered applications and RAG pipelines.
- Strong understanding of embeddings, transformers, prompt engineering / orchestration, and NLP techniques.
- Hands-on experience with vector databases (FAISS, Pinecone, Qdrant, Weaviate, Milvus).
- Familiarity with LangChain, LLMOps, and ML deployment workflows.
- Experience with containerized deployments (Docker / Kubernetes) and cloud platforms.
- Exposure to both open-weight LLMs and hosted APIs. Nice to Have - Experience in healthcare / healthtech;
knowledge of HIPAA-compliant systems.
Familiarity with autonomous agent frameworks (LangGraph, AutoGen, CrewAI).Understanding of clinical NLP ontologies (SNOMED CT, ICD, UMLS).Contributions to open-source AI / ML projects or published proofs-of-concept.Experience building real-time SaaS applications powered by AI.Exposure to multimodal retrieval (structured + unstructured data, including medical images). Soft Skills & Expectations - Bias for action : eager to prototype fast while caring about reliability in a healthcare context.Clear communicator who documents clean code and shares progress proactively.Comfortable working independently in an ambiguous, fast-paced startup environment.Flexible for early / late standups with global teams. What We Offer - Opportunity to shape one of the first LLM-powered healthcare copilots at scale.Autonomy, trust, and ownership in a results-driven team.Direct mentorship from senior AI researchers and clinicians.Chance to publish technical blogs or papers on healthcare AI.Flexible remote setup with a Hyderabad base.Competitive salary with performance bonuses.