Gen AI Data Engineer

Position Overview

Generative AI / LLM Engineer

Key Responsibilities

• Design, build, and optimize

  Generative AI and LLM-based applications

  using frameworks such as LangChain, LlamaIndex, AutoGen, and Semantic Kernel.
• Develop and maintain

  RAG (Retrieval-Augmented Generation)

  pipelines using vector databases including FAISS, Pinecone, Qdrant, Milvus, Chroma DB, and Azure Cosmos DB.
• Implement

  end-to-end ETL pipelines

  , data preprocessing workflows, and automation for processing large volumes of documents (1,000–2,000+).
• Work with

  Azure AI Services

  including Azure AI Studio, Azure AI Search, Azure Cosmos DB, and Azure Machine Learning for scalable model deployment.
• Build, fine-tune, evaluate, and integrate

  LLMs using PyTorch, TensorFlow, Hugging Face

  , and related ecosystem tools.
• Develop AI agents, embedding systems, and multimodal solutions involving text, images, and structured/unstructured data.
  
• Perform

  document and image processing

  using PyPDF, PyOCR, and OpenCV.
• Collaborate with cross-functional teams to translate business needs into AI-driven solutions.
  
• Create dashboards and insights using

  Power BI

  or

  Tableau

  .
• Optimize prompt engineering strategies and contribute to agentic AI workflows.
  
• Ensure accuracy, scalability, and performance of deployed AI applications.
  

Required Skills & Qualifications

• Strong proficiency in

  Python

  and AI/ML development.
• Hands-on experience with

  PyTorch, TensorFlow, Hugging Face, OpenCV

  , and GenAI tools.
• Expertise in

  LangChain, LangSmith, LlamaIndex, AutoGen, Semantic Kernel

  .
• Experience with

  Azure AI Services

  , Azure AI Search, Cosmos DB, and Azure ML.
• Strong understanding of

  vector databases

  : FAISS, Pinecone, Qdrant, Milvus, Chroma DB.
• Deep understanding of

  RAG pipelines, embeddings, agentic workflows, and LLM architectures

  .
• Experience with

  ETL pipelines

  , data engineering, and automation at scale.
• Knowledge of

  document processing

  using PyPDF, PyOCR, and OpenCV.
• Ability to visualize data using

  Power BI or Tableau

  .
• Excellent problem-solving skills and ability to work in fast-paced environments