Description

You will architect and build production-grade Generative AI systems, focusing on intelligent agents and Retrieval-Augmented Generation (RAG) applications.

This role is on-site.

Responsibilities

• Design and implement RAG pipelines, including document chunking, embedding generation, and retrieval systems to enhance model performance with external knowledge sources.
• Develop custom AI agents using LLMs and multi-modal models for autonomous decision-making and task execution.
• Build advanced MS Copilot Studio agents, including custom plugin development, adaptive orchestration of multiple skills, contextual memory management, and dynamic prompt engineering.
• Manage end-to-end data pipelines for pre-processing, augmentation, and synthetic data generation to optimize model training.
• Integrate enterprise applications using Copilot’s built-in connectors and create scalable logical flows for complex business processes.

Required Skills

• 10+ years of software engineering experience with advanced proficiency in Python.
• Deep hands-on experience with AI-centric libraries: TensorFlow, PyTorch, and Hugging Face Transformers.
• Proven track record of deploying scalable GenAI systems and LLM-based applications in production.
• Expertise in implementing complex algorithms for generative model optimization.
• Strong experience with data handling practices: cleaning, labeling, and structuring datasets for AI workflows.
• Proficiency in MS Copilot Studio Agent Builder, including secure data handling and workflow design.
• Ability to architect multi-modal models and manage agent orchestration triggers.

Preferred Skills

• Experience with multi-modal model orchestration.
• Background in synthetic data generation.

Key Skills

Education

Any Graduate