Proven track record in delivering Generative AI/LLM solutions in production environments. Minimum 4 years of programming experience with Python, Scala, or Java. At least 2 years of hands-on experience with Generative AI or conversational AI projects. Experience deploying traditional ML and deep learning models at scale. Strong experience with PyTorch, TensorFlow, Scikit-learn, and relevant AI libraries. Familiarity with vector search, embeddings, and semantic search architectures. Understanding of ML Ops best practices for production deployments.