onsite
AI/ML Engineer - Gemini - TechYantram Solutions
ML Engineer
Lead the design and deployment of AI models on Gemini, ChatGPT, and Copilot, building robust RAG pipelines and leveraging Vertex AI on Google Cloud to deliver scalable, context-aware machine learning solutions.
About the role
Key Responsibilities
- Design, develop, and deploy AI models using Gemini, ChatGPT, and Copilot to solve complex business problems.
- Build and maintain Retrieval-Augmented Generation (RAG) pipelines for knowledge generation and retrieval.
- Implement and optimize Model Context Protocol (MCP) to enhance model performance and scalability.
- Integrate Vertex AI services on Google Cloud Platform for model training, deployment, and monitoring.
- Collaborate with cross‑functional teams to translate business requirements into technical solutions.
Requirements
- Proven experience with Gemini, ChatGPT, or similar large language models.
- Strong background in RAG pipeline development and knowledge base construction.
- Hands‑on expertise with Vertex AI and Google Cloud Platform services.
- Solid understanding of Model Context Protocol and its application in production.
- Excellent problem‑solving skills and ability to work independently in a fast‑paced environment.