Location: Baner,Pune Experience: 5+ Years
About the Role:
We are looking for a Generative AI Engineer with deep expertise in Large Language Models (LLMs) to lead AI strategy, architecture, and development initiatives. This role demands hands-on experience in Retrieval-Augmented Generation (RAG), multi-agent AI frameworks, vector databases, and AI security. You’ll lead a team focused on building scalable, production-ready LLM-driven applications, including Conversational AI chatbots, AI-powered automation, and enterprise AI workflows.Key Responsibilities:
AI Leadership & Solution Architecture
- Design and define end-to-end AI architectures integrating LLMs, multi-agent systems, and secure AI solutions.
- Collaborate with product and business teams to translate ideas into AI-driven applications.
- Research, experiment, and implement cutting-edge AI advancements in RAG pipelines and LLM fine-tuning.
AI & Machine Learning Development
- Build and optimize LLM-based applications using frameworks like LangChain, LlamaIndex, and LangGraph.
- Work with vector databases such as FAISS, Qdrant, or Chroma for efficient knowledge retrieval.
- Leverage multi-agent AI frameworks (e.g., AutoGen) for intelligent automation.
- Implement AI security mechanisms — Guardrails, LLM Guard, and AI Red Teaming — ensuring safe and ethical AI use.
- Develop Conversational AI chatbots using NLP and LLM frameworks.
- Utilize TensorFlow and PyTorch for deep learning and fine-tune open-source LLMs for enterprise use.
API & Backend Engineering
- Build and optimize RESTful APIs using FastAPI.
- Work with relational and NoSQL databases for AI-driven applications.
- Design scalable microservices architectures for deploying AI models efficiently.
- Integrate and deploy LLMs for real-time, low-latency AI solutions.
Cloud & DevOps (Preferred Skills)
- Experience with AWS or Azure for deploying scalable AI systems.
- Familiarity with Docker and Kubernetes for containerized deployments.
- Understanding of CI/CD pipelines for automated model deployment.
