Senior AI Engineer

Location: Bengaluru

Work mode: Remote

Type: Full Time

Experience: 3–6 years

Key Skills: GenAI & LLM Development, RAG Pipeline Development, Vector Databases, LLM Evaluation & Evals, Python & FastAPI, MCP & Agentic AI, Hugging Face, Docker & Kubernetes/MLOps

What youll be working on

VisioGen is building the future of AI-powered healthcare by developing human-verified clinical communication solutions for ophthalmology practices. We combine cutting-edge Generative AI with clinical expertise to build scalable, production-ready applications that enhance patient engagement and improve healthcare delivery.

Were looking for a Senior AI Engineer to help design, build, and scale the GenAI systems powering the platform, from retrieval and reasoning to evaluation and real-time data pipelines.

What youll do

• Design, build, and maintain GenAI and LLM-based features across the VisioGen platform
• Develop and optimize RAG (Retrieval-Augmented Generation) pipelines, including data ingestion, chunking, retrieval, and real-time data updates
• Build, tune, and maintain vector database infrastructure to support semantic search and retrieval workflows
• Design and run evaluation frameworks (evals) to continuously monitor and improve model accuracy, quality, and safety
• Develop and maintain backend services using Python and FastAPI
• Build and extend agentic tooling using Model Context Protocol (MCP)
• Fine-tune, evaluate, and deploy models using the Hugging Face ecosystem
• Containerize and deploy services with Docker, and orchestrate with Kubernetes (K8s)
• Own MLOps practices across the model lifecycle: CI/CD, monitoring, versioning, and retraining pipelines
• Partner closely with product, clinical, and engineering stakeholders to translate requirements into robust, scalable AI systems
• Support a smooth knowledge transition as the team grows, and contribute to the broader AI roadmap

What were looking for

• 3–6 years of experience in AI/ML engineering
• Hands-on experience building GenAI and LLM-powered applications
• Proven experience designing and shipping RAG systems in production
• Experience building evaluation frameworks (evals) for LLM/GenAI systems
• Working knowledge of vector databases
• Experience with data ingestion pipelines and real-time data update mechanisms
• Strong proficiency in Python and FastAPI
• Familiarity with Model Context Protocol (MCP)
• Experience with Hugging Face libraries and models
• Hands-on experience with Docker and Kubernetes
• Experience with MLOps practices and tooling (CI/CD for ML, model monitoring, and versioning)
• Strong problem-solving and analytical skills, with the ability to work through ambiguous technical challenges
• Experience in healthcare, medtech, or another regulated industry
• Exposure to LLM observability/tracing tools (e.g., Langfuse)
• Experience with multilingual or multi-channel conversational AI systems