Description

Lead the architecture, development, and optimization of the GenAI product platform, including StreamSync, RAGCore, and DocForge, while mentoring ML scientists and driving technical decisions.

This role is on-site.

Responsibilities

• Architect scalable ML pipelines for analyzing Solution Architecture Documents (SADs) and enterprise data.
• Design and optimize Retrieval-Augmented Generation (RAG) systems for enterprise document processing.
• Develop advanced NLP solutions for document analysis, knowledge extraction, and LLM integration.
• Manage ML model evaluation, optimization, and deployment strategies using MLOps practices.
• Mentor ML scientists and guide infrastructure and model selection decisions.

Required Skills

• 5+ years of experience in machine learning engineering.
• Expert proficiency in Python and ML frameworks such as PyTorch or TensorFlow.
• Deep expertise in NLP, Large Language Models (LLMs), and vector embeddings.
• Hands-on experience with LangChain and Llama-index.
• Practical knowledge of RAG systems and vector databases (e.g., CosmosDB).
• Experience with AWS and Azure cloud platforms.
• Proficiency in API development and containerization.
• Understanding of MLOps practices and production deployment.

Preferred Skills

• Master's degree in Computer Science, Machine Learning, or a related field.

Key Skills

Education

Master's degree