Gen AI

GenAI Engineer Location: Santa Clara, CA - 5 days onsite Onsite interview Duration: 1 yr About the Role: We are seeking a highly skilled and innovative AI Engineer to join our team and lead the development of intelligent AI agents and Retrieval-Augmented Generation (RAG)-based applications. This role is ideal for someone passionate about pushing the boundaries of applied AI, with hands-on experience in building scalable, production-grade Generative AI (GenAI) systems and advanced Copilot Studio agent capabilities. Key Responsibilities: Demonstrate advanced programming expertise, particularly in Python, with deep proficiency in AI-centric libraries such as TensorFlow, PyTorch, and Hugging Face Transformers. Architect and implement Retrieval-Augmented Generation (RAG) pipelines to enhance model performance using external knowledge sources, including document chunking, embedding generation, and retrieval systems. Design, develop, and deploy Custom AI agents capable of autonomous decision-making and task execution using LLMs and multi-modal models. Implement and manipulate complex algorithms essential for developing and optimizing generative AI models. Manage data pipelines involving data pre-processing, augmentation, and synthetic data generation to enhance model training and performance. Ensure robust data handling practices including cleaning, labeling, and structuring datasets for generative AI workflows. Design MS Copilot Studio Agent Builder advanced skills, including custom plugin development, adaptive orchestration of multiple AI skills and APIs, contextual memory management, dynamic prompt engineering, and secure data handling. Agent Orchestration: Build multi-turn agents that adapt and chain AI skills and APIs. Trigger Management: Configure message, data, scheduled, and webhook triggers. Automation Workflow: Design workflows with Power Automate for task automation. Flow Design: Create logical, scalable flows for complex business processes. Tool Integration: Use Copilot’s built-in connectors to integrate enterprise apps and services seamlessly. Required Qualifications: Bachelor’s or Master’s degree in Computer Science, AI/ML, or related field. 3+ years of experience in AI/ML engineering, with at least 1 year focused on Generative AI. Hands-on experience with RAG architectures, including document chunking, embedding generation, and retrieval systems. Proficiency in Python and familiarity with libraries such as Hugging Face, Transformers, OpenAI API, and PyTorch/TensorFlow. Experience with Agentic AI frameworks (LangGraph, OpenAI SDK, AutoGen, CrewAI) and building agent accelerators using platforms like Copilot Studio or AWS Bedrock AgentsCore Strong understanding of LLM capabilities, limitations, and prompt engineering techniques. Experience with cloud platforms and containerization (Docker, Kubernetes). Preferred Qualifications: Experience with fine-tuning LLMs or training custom models. Familiarity with multi-modal AI (text, image, audio). Contributions to open-source GenAI projects or publications in AI conferences. Experience with CI/CD pipelines for ML model deployment.