Senior Generative AI Engineer

As a Senior Generative AI Engineer (RAG Python LLMs) at our IT company based in Pune, you will play a crucial role in engineering next-generation AI experiences. You will design, configure, and optimize intelligent AI-powered search and retrieval systems using Kore.ai SearchAI. Your expertise in LLM-powered retrieval architectures, content ingestion pipelines, retrieval quality evaluation, and enterprise AI search optimization will be instrumental in enhancing search relevance, retrieval accuracy, and content intelligence across enterprise platforms. Key Responsibilities: - Configure and optimize Kore.ai SearchAI pipelines for enterprise AI search use cases - Design and implement effective chunking strategies for structured and unstructured enterprise content - Manage content ingestion workflows and retrieval optimization for LLM-based search systems - Perform retrieval quality testing, relevance evaluation, and response accuracy analysis - Support migration activities from SearchAssist to SearchAI platforms - Validate enterprise content against technical standards and ingestion requirements - Work closely with cross-functional teams to improve search relevance and user experience - Analyze retrieval patterns and optimize AI search performance using data-driven insights - Troubleshoot indexing, ingestion, retrieval, and ranking-related issues - Collaborate with AI/ML teams to enhance semantic search and agentic AI capabilities Qualifications Required: - Strong experience with Kore.ai SearchAI / SearchAssist platforms - Hands-on expertise in content chunking strategies, AI search pipelines, and retrieval optimization - Familiarity with semantic search systems and LLM-powered retrieval systems - Understanding of vector search, embeddings, and AI content ingestion pipelines - Proficiency in Python programming and working with REST APIs - Knowledge of unstructured content processing and indexing - Experience with retrieval quality testing and evaluation frameworks - Desirable: Exposure to Agentic AI frameworks, vector databases such as Pinecone or Weaviate, LangChain, LlamaIndex, or similar AI orchestration frameworks, and understanding of AI governance and content validation standards Please note that candidates with 7+ years of experience are preferred, and expertise with Kore.ai SearchAI/SearchAssist is highly valued. Freshers will not be considered for this position. The budget for this role is as per market standards, and immediate joiners or those with a notice period of 15 days are welcome to apply. As a Senior Generative AI Engineer (RAG Python LLMs) at our IT company based in Pune, you will play a crucial role in engineering next-generation AI experiences. You will design, configure, and optimize intelligent AI-powered search and retrieval systems using Kore.ai SearchAI. Your expertise in LLM-powered retrieval architectures, content ingestion pipelines, retrieval quality evaluation, and enterprise AI search optimization will be instrumental in enhancing search relevance, retrieval accuracy, and content intelligence across enterprise platforms. Key Responsibilities: - Configure and optimize Kore.ai SearchAI pipelines for enterprise AI search use cases - Design and implement effective chunking strategies for structured and unstructured enterprise content - Manage content ingestion workflows and retrieval optimization for LLM-based search systems - Perform retrieval quality testing, relevance evaluation, and response accuracy analysis - Support migration activities from SearchAssist to SearchAI platforms - Validate enterprise content against technical standards and ingestion requirements - Work closely with cross-functional teams to improve search relevance and user experience - Analyze retrieval patterns and optimize AI search performance using data-driven insights - Troubleshoot indexing, ingestion, retrieval, and ranking-related issues - Collaborate with AI/ML teams to enhance semantic search and agentic AI capabilities Qualifications Required: - Strong experience with Kore.ai SearchAI / SearchAssist platforms - Hands-on expertise in content chunking strategies, AI search pipelines, and retrieval optimization - Familiarity with semantic search systems and LLM-powered retrieval systems - Understanding of vector search, embeddings, and AI content ingestion pipelines - Proficiency in Python programming and working with REST APIs - Knowledge of unstructured content processing and indexing - Experience with retrieval quality testing and evaluation frameworks - Desirable: Exposure to Agentic AI frameworks, vector databases such as Pinecone or Weaviate, LangChain, LlamaIndex, or similar AI orchestration frameworks, and understanding of AI governance and content validation standards Please note that candidates with 7+ years of experience are preferred, and expertise with Kore.ai SearchAI/SearchAssist is highly valued. Freshers will not be considered for this position. The budget for this