Advanced Python development for ML/AI workloads • End-to-end ML lifecycle: model training, evaluation, fine-tuning, and labeling/tagging workflows • Generative AI systems design, including LLM-based application development • Prompt engineering optimization for large language models • Document AI pipelines: OCR/extraction, parsing, normalization, and text chunking for structured & unstructured data • Embedding generation pipelines for semantic search and retrieval • Vector similarity search implementation using vector databases • ML model integration with Vector DBs and MongoDB • Production-grade ML engineering: scalable, maintainable, and deployment-ready code. • Develop and deploy machine learning and GenAI solutions using Python • Design and optimize prompt engineering strategies for LLM-based applications • Build document extraction, parsing, and chunking pipelines for structured and unstructured data • Train, evaluate, and fine-tune ML models; manage tagging and labeling workflows • Implement embedding generation and vector search solutions • Integrate ML models with Vector DBs and MongoDB • Ensure code quality, scalability, and production readiness.