IN_Manager_Gen AI_D&A_Advisory_PAN India

Job Description Job Description: We are looking for a highly motivated and hands-on AI Engineer with 8-10 years of experience to design, develop, deploy, and optimize enterprise-grade Generative AI and Agentic AI solutions . The ideal candidate will have strong software engineering fundamentals, experience building AI-powered applications, and hands-on expertise with Azure AI Foundry, Amazon Bedrock, LLMs, RAG architectures, and agent frameworks . This role is focused on implementation and delivery, requiring the candidate to translate architectural designs into scalable production solutions while collaborating closely with AI Architects, Product Teams, and business stakeholders. Job Title: IN_Manager_Gen AI_D&A_Advisory_PAN India Roles and Responsibilities Design, develop, and deploy production-ready Generative AI applications. Build and optimize Agentic AI solutions , including autonomous agents, multi-agent workflows, and tool integrations. Develop RAG-based applications leveraging enterprise knowledge sources and vector databases. Integrate foundation models from Azure AI Foundry, Amazon Bedrock, OpenAI, Anthropic, or similar platforms. Implement prompt engineering, prompt chaining, and advanced orchestration workflows. Develop APIs, microservices, and backend components supporting AI-powered applications. Design and implement evaluation frameworks to measure LLM quality, hallucination rates, accuracy, latency, and business outcomes. Fine-tune, benchmark, and optimize AI application performance, scalability, and cost. Build integrations with enterprise systems, databases, Microsoft 365, CRM, ERP, and third-party platforms. Implement security, governance, observability, monitoring, and guardrails for AI applications. Collaborate with architects and business teams to convert use cases into technical solutions. Troubleshoot complex AI application issues and drive continuous improvement. Contribute to reusable AI accelerators, frameworks, and best practices. Mandatory Skills: 4-8 years of software engineering experience with at least 2+ years in Generative AI development. Strong hands-on experience with Large Language Models (LLMs) and Generative AI application development. Experience with Azure AI Foundry , Amazon Bedrock , or equivalent enterprise AI platforms. Strong expertise in building and deploying RAG (Retrieval Augmented Generation) solutions. Hands-on experience with agent frameworks such as LangGraph, LangChain, Semantic Kernel, CrewAI, AutoGen , or similar. Experience with vector databases such as Azure AI Search, Pinecone, Weaviate, Chroma, OpenSearch, or Elasticsearch . Strong programming expertise in Python and API development using FastAPI, Flask, or similar frameworks. Experience implementing LLM evaluation frameworks, testing, and performance benchmarking. Good understanding of AI architecture fundamentals, model selection, embeddings, chunking strategies, and grounding techniques. Experience with cloud-native development on Azure or AWS. Strong understanding of software engineering best practices, CI/CD, testing, and version control. Preferred Skill: Experience with multimodal AI solutions involving text, image, audio, or video models. Exposure to model fine-tuning, LoRA, PEFT, or domain adaptation techniques. Experience with Kubernetes, Docker, and containerized deployments. Knowledge of MLOps/LLMOps platforms and AI observability tools. Familiarity with Responsible AI, AI governance, and AI security principles. Experience integrating AI solutions with Microsoft Copilot Studio, Power Platform, Microsoft Fabric, or enterprise data platforms. Certifications in Azure AI, AWS AI/ML, Generative AI, or cloud technologies. Highest Education : Btech Years Of Experience : 8-10 years

• Experience: 2+ years
• Seniority: Entry Level
• Education: Bachelor's degree required
• Languages: English