Generative AI Engineer

Overview

Junior Generative AI Engineer role in Bengaluru, building LLM and RAG-based AI applications with a senior engineering team.

What you'll do

• Develop and implement AI-powered applications using LLMs and Generative AI.
• Build and optimize RAG pipelines for intelligent document retrieval and question-answering systems.
• Work with LLM frameworks such as LangChain, LlamaIndex, and Hugging Face.
• Integrate LLM APIs such as OpenAI, Azure OpenAI, or open-source models.
• Implement embeddings, semantic search, and vector databases.
• Develop Python-based APIs and backend services using FastAPI or Flask.
• Perform prompt engineering, LLM response evaluation, and model optimization.
• Collaborate with senior engineers to develop and deploy scalable AI solutions.

What you'll need

• B.E./B.Tech/M.Tech/MCA in Computer Science, AI/ML, Data Science, or a related field.
• 0–1 year of relevant experience, including internships or project work.
• Strong problem-solving and analytical skills.
• Good communication skills and willingness to learn emerging AI technologies.
• Strong knowledge of Python.
• Basic understanding of LLMs, prompt engineering, and transformers.
• Understanding of document chunking, embeddings, retrieval, and vector search.
• Frameworks: LangChain, LlamaIndex, or Hugging Face.
• Vector databases: FAISS, ChromaDB, Pinecone, or similar.
• REST APIs and LLM API integration.
• Basic SQL and database concepts.
• Git, Jupyter Notebook, and VS Code.

Nice to have

• Exposure to AI agents, tool calling, and agentic AI workflows.
• Knowledge of fine-tuning techniques such as LoRA and PEFT.
• Familiarity with AWS, Azure, or GCP.
• Basic understanding of Docker and AI application deployment.
• Experience with academic or personal projects involving LLMs, RAG, or chatbots.

Details

• Location: Bengaluru (only Bengaluru-based candidates preferred).
• Experience: 0–1 year.
• Notice period: Immediate joiner.