Gen AI Engineer

KEY RESPONSIBILITIES • Design, build, and deploy end-to-end Generative AI applications using LLMs, vision-language models, and multimodal AI. • Proficiency in Python with strong experience using GenAI/LLM frameworks such as LangChain, LlamaIndex, CrewAI, or HuggingFace Transformers. • Develop applications using OpenAI, Azure OpenAI, or custom-deployed open-source models (e.g., LLaMA, DeepSeek, Mistral). • Create and manage agent-based architectures for task orchestration using frameworks like AutoGen, CrewAI, or Semantic Kernel. • Implement Retrieval-Augmented Generation (RAG) systems using FAISS, Weaviate, or Azure Cognitive Search. • Work with document loaders, chunking strategies, vector embeddings, and prompt engineering techniques for optimal model performance. • Build and deploy AI-powered apps using FastAPI (backend), React/Streamlit/Gradio (frontend), and PostgreSQL or vector DBs (Pinecone, Qdrant). • Design and operationalize GenAI workflows using Docker, Kubernetes, and MLOps tools (e.g., MLFlow, Azure ML). • Integrate AI with cloud-native services (e.g., Azure Functions, EventHub, Cosmos DB, OneLake, Azure Fabric). • Continuously improve model accuracy and relevance through fine-tuning, prompt tuning, and response evaluation techniques. • Ensure alignment of GenAI solutions with product goals and compliance with security, governance, and data privacy standards. • Evaluate trade-offs across different model providers (OpenAI, Azure, Anthropic, open-source) based on latency, cost, accuracy, and IP risk. • Collaborate with cross-functional teams including Product, Data Engineering, and QA to ensure robust deployment of GenAI features. • Implement logging, monitoring, and feedback loops to support performance tuning and hallucination mitigation