AI ML Engineer

Key Responsibilities

• Design and develop AI/ML and Generative AI solutions using LLMs (Large Language Models).
• Build and implement RAG (Retrieval-Augmented Generation) architectures for intelligent applications.
• Develop and optimize prompt engineering strategies and fine-tune models using SFT (Supervised Fine-Tuning).
• Work with LLM platforms such as OpenAI and Anthropic (Claude AI).
• Build AI workflows using LangChain and LangGraph for orchestration of LLM-based applications.
• Develop intelligent document processing solutions using platforms such as Rossum, Hyperscience, Nanonets, and Infrrd.
• Implement document AI solutions using Microsoft Azure AI Document Intelligence, AWS Textract, LandingAI (ADE Split), and LlamaParse.
• Work with advanced document understanding models such as LayoutLMv3 and Donut for structured data extraction.
• Implement and manage vector databases for semantic search and knowledge retrieval.
• Develop scalable APIs and backend services using Flask and/or FastAPI.
• Train and optimize models using PyTorch and TensorFlow.
• Deploy AI solutions on cloud-native platforms (AWS, GCP, Azure) with a focus on Azure AI/ML services.
• Collaborate with cross-functional teams to deliver production-ready AI systems.