Design and develop enterprise-grade Generative AI solutions using Python and up-to-date AI frameworks.
Build AI applications using LLMs, embeddings, prompts, function calling, tool usage, and agentic AI patterns.
Implement Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge retrieval and generation use cases.
Design end-to-end AI solutions covering:
Data ingestion o Data processing o Retrieval o Generation o Evaluation
Work with Agentic AI frameworks such as CrewAI, LangChain, LangGraph, LlamaIndex, AutoGen, and Langfuse.
Apply prompt engineering strategies to improve LLM accuracy, reliability, and usability.
Evaluate the suitability of fine-tuning vs RAG based on business and technical requirements.
Support LLM fine-tuning workflows including instruction tuning and supervised fine-tuning.
Manage data preparation for fine-tuning, including train/validation splits, data quality checks, and contamination prevention.
Deploy AI workloads on cloud platforms such as Azure, AWS, or GCP.
Containerize AI applications using Docker and work with basic Kubernetes concepts.
Apply model engineering best practices for scalable, reliable, and production-ready AI systems.