Generative AI Engineer (LLMs & RAG) – Healthcare SaaS
Summary
Hands-on Generative AI engineer building production RAG pipelines and LLM-powered features for a healthcare SaaS clinical assistant. Day to day: experimenting with open-source and hosted LLMs, tuning retrieval/embeddings, running evaluation and hallucination checks, and deploying on AWS/GCP/Azure with Docker/Kubernetes.
Compensation: ₹15L – ₹30L • No equity
# **Generative AI Engineer (LLMs & RAG) – Healthcare SaaS** **Location:** Remote / Hyderabad **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 deep expertise in **LLMs** and **Retrieval-Augmented Generation (RAG)**. In this role, you'll design and deliver production-grade AI systems that combine unstructured and structured healthcare data to power a next-generation clinical assistant. You will be working at the forefront of Generative AI innovation in healthcare—building safe, scalable, and high-impact solutions that influence real-world patient outcomes. --- ## **What You’ll Do** * Architect and optimize **RAG pipelines** (ingestion, embeddings, retrieval, grounding, generation). * Experiment with LLMs — **LLaMA, Mistral, Falcon**, plus **OpenAI & Anthropic APIs**. * Implement evaluation & monitoring: retrieval precision, grounding accuracy, hallucination checks, latency, safety. * Work with diverse healthcare datasets — PDFs, EHR/EMR data, CSVs, structured knowledge bases. * Deploy cloud-native AI services (AWS / GCP / Azure) with observability & security. * Collaborate with product, clinicians, DevOps, and QA to ship production features. --- ## **Must-Have Skills** * 5+ years in software/ML engineering with strong Python skills. * Proven experience building **LLM-powered applications & RAG systems**. * Strong understanding: embeddings, transformers, prompt engineering, NLP techniques. * Experience with vector DBs: **FAISS, Pinecone, Qdrant, Weaviate, Milvus**. * Familiar with LangChain, LLMOps, ML deployment workflows. * Cloud + containerization experience (Docker/Kubernetes). --- ## **Nice to Have** * Healthcare or healthtech experience; understanding of **HIPAA**. * Knowledge of agent frameworks: **LangGraph, AutoGen, CrewAI**. * Familiarity with clinical ontologies (**SNOMED CT, ICD, UMLS**). * Contributions to open-source AI/ML projects. * Experience building real-time AI SaaS systems. * Exposure to multimodal retrieval (structured + unstructured + images). --- ## **Soft Skills** * Bias for action; fast prototyping with reliability in mind. * Clear communication & strong documentation habits. * Able to work independently in a fast-moving startup environment. * Comfortable with flexible hours for global standups. --- ## **What We Offer** * Opportunity to shape one of the first **LLM-powered healthcare copilots** at scale. * Ownership, autonomy, and a high-impact environment. * Direct mentorship from senior AI researchers and clinicians. * Opportunity to publish AI/healthcare content. * Remote-friendly with optional Hyderabad base. * Competitive salary + performance bonuses.Skills
- AI
- Anthropic
- API
- AutoGen
- AWS
- Azure
- Cloud
- Cloud Native
- Containerization
- CrewAI
- DevOps
- Docker
- Embeddings
- FAISS
- GCP
- Generative AI
- Hipaa
- Kubernetes
- LangChain
- LangGraph
- LLM
- LLMOps
- Machine Learning
- Milvus
- Mistral
- NLP
- Observability
- OpenAI
- Pinecone
- Prompt Engineering
- Prototyping
- Python
- Qdrant
- RAG
- SaaS
- Transformers
- Weaviate