Generative AI Engineer

Role Overview We are looking for a skilled Generative AI Engineer to design, develop, and implement Generative AI solutions and Knowledge Layer capabilities using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI workflows. The role involves working on unstructured data processing, semantic chunking, embeddings, vector search, entity extraction, ontology development, and knowledge graphs to build intelligent, scalable, and reliable AI applications.

The ideal candidate should have strong hands-on experience in Python, LLM frameworks, API integrations, vector databases, and cloud technologies, along with an understanding of production-grade AI deployment, evaluation, monitoring, and governance.

Key Responsibilities

• Design and develop Generative AI solutions leveraging LLMs, RAG architectures, Agentic AI, and prompt engineering.
• Build knowledge layer capabilities, including unstructured data processing, semantic chunking, embeddings generation, and vector-based semantic search.
• Develop entity extraction pipelines, ontologies, and knowledge graphs to enhance knowledge representation, retrieval, and contextual understanding.
• Design and implement agentic workflows, tool calling, and MCP (Model Context Protocol) / API integrations to connect AI systems with enterprise data sources and external services.
• Develop scalable and reusable AI components, frameworks, and architectural patterns for GenAI and knowledge-driven applications.
• Implement guardrails, model evaluation frameworks, response quality checks, and monitoring mechanisms to ensure accuracy, reliability, and responsible AI usage.
• Build and integrate REST APIs and backend services using Python and relevant frameworks.
• Deploy and manage AI applications using Docker, Kubernetes, CI/CD pipelines, and cloud platforms such as AWS or Azure.
• Implement MLOps and LLMOps practices covering model deployment, versioning, evaluation, monitoring, and continuous improvement.
• Collaborate with cross-functional teams to translate business requirements into scalable and production-ready AI solutions.

Technical Skills Required

• Generative AI: Generative AI, Large Language Models (LLMs), prompt engineering, RAG, Agentic AI, AI agents.
• Knowledge Layer: Unstructured data processing, semantic chunking, embeddings, vector search, entity extraction, ontologies, knowledge graphs.
• Frameworks and Integration: Python, LangChain, LangGraph, LlamaIndex or similar frameworks, MCP, REST APIs, API integrations.
• Databases and Search: Vector databases, semantic search, and familiarity with graph databases or knowledge graph technologies.
• AI Quality and Governance: Guardrails, model evaluation, response validation, performance monitoring, and responsible AI practices.
• Cloud and Deployment: AWS and/or Azure, Docker, Kubernetes, CI/CD.
• Operational Practices: MLOps, LLMOps, model deployment, monitoring, and production lifecycle management.

Job Category: Generative AI Engineer

Job Type: Full Time

Job Location: New Delhi Pune Gurgaon

Experience: 4-10 years

Key Responsibilities

• Design and develop Generative AI solutions leveraging LLMs, RAG architectures, Agentic AI, and prompt engineering.
• Build knowledge layer capabilities, including unstructured data processing, semantic chunking, embeddings generation, and vector-based semantic search.
• Develop entity extraction pipelines, ontologies, and knowledge graphs to enhance knowledge representation, retrieval, and contextual understanding.
• Design and implement agentic workflows, tool calling, and MCP (Model Context Protocol) / API integrations to connect AI systems with enterprise data sources and external services.
• Develop scalable and reusable AI components, frameworks, and architectural patterns for GenAI and knowledge-driven applications.
• Implement guardrails, model evaluation frameworks, response quality checks, and monitoring mechanisms to ensure accuracy, reliability, and responsible AI usage.
• Build and integrate REST APIs and backend services using Python and relevant frameworks.
• Deploy and manage AI applications using Docker, Kubernetes, CI/CD pipelines, and cloud platforms such as AWS or Azure.
• Implement MLOps and LLMOps practices covering model deployment, versioning, evaluation, monitoring, and continuous improvement.
• Collaborate with cross-functional teams to translate business requirements into scalable and production-ready AI solutions.

Technical Skills Required

• Generative AI: Generative AI, Large Language Models (LLMs), prompt engineering, RAG, Agentic AI, AI agents.
• Knowledge Layer: Unstructured data processing, semantic chunking, embeddings, vector search, entity extraction, ontologies, knowledge graphs.
• Frameworks and Integration: Python, LangChain, LangGraph, LlamaIndex or similar frameworks, MCP, REST APIs, API integrations.
• Databases and Search: Vector databases, semantic search, and familiarity with graph databases or knowledge graph technologies.
• AI Quality and Governance: Guardrails, model evaluation, response validation, performance monitoring, and responsible AI practices.
• Cloud and Deployment: AWS and/or Azure, Docker, Kubernetes, CI/CD.
• Operational Practices: MLOps, LLMOps, model deployment, monitoring, and production lifecycle management.