Key Responsibilities

• Develop and fine-tune Generative AI models (LLMs, Chatbots, Vision Models).
• Build RAG pipelines, embeddings, and vector search solutions using LangChain/LlamaIndex.
• Design and optimize prompt templates, workflows, and automation chains.
• Integrate AI models into applications using Python APIs and backend systems.
• Conduct data preprocessing, model evaluation, and optimization.
• Develop POCs and AI demos for internal and client use.
• Stay updated with latest advancements in LLMs and Gen AI technologies.
• Prepare clean documentation, architecture notes, and deployment guides.

Required Skills

• 1–2 years of experience in AI/ML or Generative AI within an IT/software company.
• Strong understanding of LLMs, transformers, embeddings, vector databases.
• Hands-on experience with OpenAI, Hugging Face, LangChain, LlamaIndex, or RAG frameworks.
• Proficiency in Python and ML libraries (PyTorch/TensorFlow).
• Experience deploying models via APIs (FastAPI/Flask).
• Knowledge of Azure OpenAI / AWS / GCP.
• Strong analytical and problem-solving skills.

Preferred Skills

• Experience building chatbots, AI assistants, or automation tools.
• Exposure to LLM fine-tuning and custom model training.
• Familiarity with FAISS, Pinecone, or ChromaDB.