Padmi

Gen AI- Immediate Joiner (Gurgaon location)

Delhi NCRPosted 1 month ago
Software engineeringMid-levelFull Time; Regular
Apply at EY

Opens the source posting on shine.com

Source description

About the role

View original

Job Description (JD) GenAI / LLM / Agentic AI Engineer Position: GenAI / LLM / Agentic AI Engineer Experience: 310 Years Location: Gurgaon Education: B.E./B.Tech/M.Tech from Tier-1 Institutes (IITs, NITs, IIITs, BITS Pilani, or equivalent premier institutions) Role Overview We are seeking a highly skilled GenAI / LLM / Agentic AI Engineer to design, develop, and deploy next-generation AI solutions leveraging Large Language Models (LLMs), Agentic AI frameworks, Retrieval-Augmented Generation (RAG), and enterprise AI platforms. The candidate will work closely with business and engineering teams to build scalable, production-grade AI applications. Key Responsibilities Design and implement GenAI-powered applications using OpenAI, Azure OpenAI, Claude, Gemini, and open-source LLMs. Build Agentic AI workflows utilizing frameworks such as LangGraph, LangChain, CrewAI, AutoGen, and Semantic Kernel. Develop and optimize RAG pipelines with vector databases (Pinecone, FAISS, ChromaDB, Weaviate, Azure AI Search). Fine-tune and evaluate LLMs using modern techniques including LoRA, PEFT, and prompt engineering. Create AI agents capable of planning, reasoning, tool usage, and workflow orchestration. Establish AI governance, monitoring, observability, and model performance tracking. Integrate AI applications with enterprise systems via APIs, cloud services, and automation platforms. Collaborate with data scientists, architects, and product teams to deliver business-focused AI solutions. Required Skills Strong proficiency in Python. Hands-on experience with Generative AI, LLMs, and Agentic AI frameworks. Expertise in Prompt Engineering, RAG, Vector Databases, and AI Evaluation. Experience with LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, LlamaIndex. Knowledge of Transformer architecture and modern LLM ecosystems. Familiarity with cloud platforms such as Azure, AWS, or GCP. Experience building REST APIs and deploying AI applications in production. Strong understanding of software engineering best practices, CI/CD, and MLOps. Preferred Qualifications Experience with fine-tuning open-source LLMs (Llama, Mistral, Qwen, etc.). Knowledge of AI safety, responsible AI, and governance. Exposure to multi-agent systems and autonomous workflow orchestration. Contributions to AI open-source projects, research publications, or patents. Educational Qualification B.E./B.Tech/M.Tech in Computer Science, AI/ML, Data Science, Electronics, or related disciplines. Preferred candidates from IITs, NITs, IIITs, BITS Pilani, or other Tier-1 engineering institutions. Nice to Have Certifications in Azure AI, AWS AI/ML, or Google AI. Experience working with enterprise GenAI adoption programs. Strong problem-solving and stakeholder management skills. Job Description (JD) GenAI / LLM / Agentic AI Engineer Position: GenAI / LLM / Agentic AI Engineer Experience: 310 Years Location: Gurgaon Education: B.E./B.Tech/M.Tech from Tier-1 Institutes (IITs, NITs, IIITs, BITS Pilani, or equivalent premier institutions) Role Overview We are seeking a highly skilled GenAI / LLM / Agentic AI Engineer to design, develop, and deploy next-generation AI solutions leveraging Large Language Models (LLMs), Agentic AI frameworks, Retrieval-Augmented Generation (RAG), and enterprise AI platforms. The candidate will work closely with business and engineering teams to build scalable, production-grade AI applications. Key Responsibilities Design and implement GenAI-powered applications using OpenAI, Azure OpenAI, Claude, Gemini, and open-source LLMs. Build Agentic AI workflows utilizing frameworks such as LangGraph, LangChain, CrewAI, AutoGen, and Semantic Kernel. Develop and optimize RAG pipelines with vector databases (Pinecone, FAISS, ChromaDB, Weaviate, Azure AI Search). Fine-tune and evaluate LLMs using modern techniques including LoRA, PEFT, and prompt engineering. Create AI agents capable of planning, reasoning, tool usage, and workflow orchestration. Establish AI governance, monitoring, observability, and model performance tracking. Integrate AI applications with enterprise systems via APIs, cloud services, and automation platforms. Collaborate with data scientists, architects, and product teams to deliver business-focused AI solutions. Required Skills Strong proficiency in Python. Hands-on experience with Generative AI, LLMs, and Agentic AI frameworks. Expertise in Prompt Engineering, RAG, Vector Databases, and AI Evaluation. Experience with LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, LlamaIndex. Knowledge of Transformer architecture and modern LLM ecosystems. Familiarity with cloud platforms such as Azure, AWS, or GCP. Experience building REST APIs and deploying AI applications in production. Strong understanding of software engineering best practices, CI/CD, and MLOps. Preferred Qualifications Experience with fine-tuning open-source LLMs (Llama, Mistral, Qwen, etc.). Knowledge of AI safety, responsible AI, and governan

One address, no account. We’ll tell you when matching roles go live.

More at EY

Related open roles

View all roles