Role : Gen AI- Data Engineer
Key Responsibilities :
- Architect and implement generative AI and LLM-powered applications using frameworks such as LangChain, LangSmith, LlamaIndex, AutoGen, and Semantic Kernel.
- Build scalable cloud-based solutions using Microsoft Azure AI Services , integrating with AWS (Boto3) and Google Cloud (Vertex AI).
- Design and optimize vector search and database solutions using Chroma DB, FAISS, Pinecone, Qdrant, Milvus, and Cosmos DB to
enable efficient information retrieval.
Apply AI techniques including Retrieval-Augmented Generation (RAG), embedding generation, prompt engineering, fine-tuning LLMs, and Agentic AI approaches.Perform document and image processing using Python-based tools such as PyPDF, PyOCR, and OpenCV.Develop APIs and web applications to deploy AI models using frameworks like FastAPI, Flask, Streamlit, or Gradio.Collaborate with cross-functional teams to integrate AI models with visualization tools such as Power BI and Tableau for business insights.Continuously monitor, troubleshoot, and improve AI workflows to ensure robustness, scalability, and security.Skills :
Proficient in Python programming, with experience in PyTorch, TensorFlow, and Hugging Face libraries.Hands-on experience with generative AI and LLM frameworks including LangChain, LangSmith, LlamaIndex, AutoGen, SemanticKernel.
Skilled in cloud AI services such as Microsoft Azure AI Studio, Azure AI Search, Azure Cosmos DB, Azure Machine Learning, AWSBoto3, and Google Cloud Vertex AI.
Experience with vector databases and search technologies including Chroma DB, FAISS, Pinecone, Qdrant, Milvus, and Cosmos DB.Expertise in ETL pipeline design, data preprocessing, and managing multimodal workflows at scale.Knowledge of AI methodologies such as Retrieval-Augmented Generation (RAG), embedding techniques, prompt engineering, andfine-tuning LLMs.
Familiarity with document and image processing tools like PyPDF, PyOCR, and OpenCV.Ability to develop and deploy AI models through APIs and web frameworks such as FastAPI, Flask, Streamlit, or Gradio.Experience with data visualization tools like Power BI and Tableau is a plus.(ref : hirist.tech)