About the Role

We are looking for a highly motivated GenAI Developer Intern to join our AI team in GIFT City. This role is ideal for learners who want hands-on experience building next-generation AI solutions using Large Language Models (LLMs), prompt engineering, retrieval systems, and intelligent automation.
You will work closely with our engineering team to experiment, fine-tune, and integrate GenAI models across real business use cases in healthcare, fintech, customer experience, enterprise workflows, and automation products.

Key Responsibilities:

• Assist in building LLM-powered applications for chatbots, assistants, summarization tools, analytics agents, and workflow automation.
• Develop and refine prompts, instructions, and model behaviors for different use cases.
• Work on RAG pipelines including embedding models, vector databases, and context retrieval flows.
• Integrate open-source and commercial LLMs (OpenAI, Llama, Mistral, etc.) into backend systems.
• Support fine-tuning, model evaluation, and output quality testing.
• Help build scalable APIs for GenAI workflows using Node.js or Python.
• Experiment with advanced topics such as voice agents, multi-modal AI, function calling, and agent frameworks.
• Collaborate with DevOps to containerize and deploy GenAI services.
• Document your experiments, findings, and improvements for internal teams.

Required Skills

• Strong proficiency in Python or JavaScript/TypeScript.
• Understanding of AI/ML concepts and familiarity with LLM fundamentals.
• Exposure to frameworks like LangChain, LlamaIndex, or OpenAI SDKs.
• Ability to design and test prompts for chat, reasoning, extraction, and summarization tasks.
• Basic knowledge of embeddings, vector search, and RAG workflows.
• Good problem-solving skills and eagerness to learn new GenAI technologies.

Nice-to-Have Skills

• Experience with any open-source LLM (Llama, Mistral, Gemma, etc.).
• Familiarity with vector databases such as Pinecone, Weaviate, ChromaDB, or Qdrant.
• Understanding of agentic systems, tool calling, or workflow orchestration.
• Exposure to Docker, cloud services (AWS/GCP/Azure), and API development.
• Knowledge of multimodal AI (vision + LLMs), TTS, STT, or voice bots.

Interested candidates may apply at [email protected]