Generative AI Engineer

About Client: Our Client is a leading technology solutions company with a strong engineering pedigree. Headquartered in Pune, India, they are part of the USD 4.4 billion RPG Group, serving over 145 global clients. It has been a public-listed company for over 50 years, disrupting the status quo through our deep engineering capabilities, innovation, and velocity. Our 10,500+ workforce across 30+ global locations delivers cutting-edge digital solutions, unlocks growth, and empowers our clients to thrive and succeed in a world of constant change. Job Title :Generative AI Engineer Location:Pune ·Experience: 9- 12 Years Work Mode : WFO Job Type : Full Time Notice Period:- 0-30 Days Detailed JD: Key SkillS: GEN AI+Python Key Responsibilities: • Generative AI Systems Design: Architect scalable, high-performance applications powered by Generative AI models (e.g., LLMs, diffusion models), with a focus on real-world usability and business integration. • Prompt Engineering & RAG Pipelines: Design and implement optimized prompt strategies and Retrieval-Augmented Generation (RAG) workflows using LangChain and similar frameworks. • Agentic AI & Autonomous Workflows: Develop and manage intelligent agents capable of multi-step reasoning, planning, and decision-making using frameworks like LangChain Agents or custom implementations. • Vector Store Integration: Design and integrate vector databases for semantic search and document retrieval in GenAI workflows. • End-to-End AI Application Development: Build and deploy AI-driven applications from scratch using Python and modern ML/AI toolkits. Ensure clean integration with APIs, databases, and frontend services. • Microservices & API Development: Create modular, maintainable backend services using microservices architecture. Ensure RESTful APIs for smooth communication. • CI/CD & DevOps: Develop and maintain CI/CD pipelines for model and app deployment. Ensure reproducibility, automated testing, and smooth rollout using tools like GitHub Actions, GitLab CI/CD, or Jenkins. • Database Management: Use PostgreSQL and NoSQL databases effectively in storing structured and unstructured data, with focus on performance, indexing, and scaling. • Performance Optimization: Continuously monitor, benchmark, and optimize applications for performance, scalability, and cost-efficiency across cloud and on-prem environments. • Collaboration & Mentorship: Work closely with product managers, AI researchers, and junior developers. Lead by example and provide technical mentorship in AI system design and production-readiness. Required Qualifications: • Technical Expertise: Strong proficiency in Python (mandatory) and experience with AI/ML libraries like FastAI, Hugging Face Transformers, and OpenAI APIs. Experience implementing LangChain workflows, prompt chaining, agents, tools, and memory systems. Hands-on experience building RAG systems using vector DBs like FAISS, Pinecone, Weaviate, or Chroma. Solid understanding of Generative AI technologies (LLMs, image/video generation, embeddings). Working knowledge of Agentic AI concepts for building autonomous tools and applications. • Backend & Architecture: Strong skills in system design, API development, and microservices-based backend architecture. Experience with PostgreSQL and NoSQL databases (e.g., MongoDB, DynamoDB). • Cloud & DevOps: Familiarity with CI/CD pipelines, containerization (Docker), and cloud deployments (AWS/GCP/Azure). Git-based version control and collaborative development workflows. • Communication & Leadership: Ability to translate AI research into production-ready applications. Strong collaboration skills and experience leading engineering efforts or mentoring peers. Preferred (Nice to Have): • Experience working with LLMOps tools • Exposure to data labeling, fine-tuning, or custom LLM training. • Familiarity with streaming architectures or real-time AI inference. Interested candidate can also share their CV at [HIDDEN TEXT]