AI/ML Engineer (LLM & RAG)

About the role

Supportsoft Technologies is looking for a hands-on AI/ML Engineer in Jaipur to build and deploy AI-powered features across web and mobile applications. The work covers real-world use cases such as chatbots, document intelligence, recommendation systems and workflow automation. The position is full-time and based in the office.

Key responsibilities

• Design and develop AI-powered solutions using Large Language Models (LLMs)
• Build RAG (Retrieval-Augmented Generation) pipelines using vector databases
• Integrate AI services (OpenAI, Claude, open-source models)
• Develop APIs using Python (FastAPI/Flask) for AI services
• Work with frontend and backend teams to integrate AI into production apps
• Optimize prompts, latency and cost of AI usage
• Fine-tune or customize models when required (optional but preferred)

Required profile

• Strong Python programming skills
• Experience with LLM frameworks (LangChain, LlamaIndex)
• Knowledge of embeddings and vector databases (Pinecone, Weaviate, Supabase)
• Experience with REST APIs and microservices architecture
• Understanding of NLP concepts

Good to have

• Docker and cloud platforms (AWS, GCP, Azure)
• Exposure to open-source models (Llama, Mistral)
• Basic understanding of frontend/backend integration