Key Skills: LLM, Lang chain, Python, Gen AI, Retrieval-Augmented Generation (RAG), Cloud, AI/ML, Pytorch
Roles and Responsibilities:
Design and develop RESTful APIs and web services using Python frameworks such as Flask, Django, or FastAPI.
Build and optimize GenAI/LLM solutions, including Retrieval-Augmented Generation (RAG) pipelines for production use cases.
Research, integrate, and evaluate state-of-the-art generative AI models and techniques to improve product functionality.
Lead, mentor, and manage a team of developers; set goals, delegate tasks, and drive timely delivery.
Ensure quality through code reviews, testing, and validation of AI models for accuracy, reliability, and scalability.
Skills Required:
10 - 15 years of relevant experience in backend and AI/GenAI engineering, including leadership/management.
Python development with robust backend engineering fundamentals.
GenAI and LLM implementation experience, including RAG-based systems.
LangChain experience for building natural language understanding and generation workflows.
Production mindset for deploying and validating AI/LLM solutions with reliable backend integrations.
Valuable to Have
PyTorch experience for building and optimizing generative models.
Cloud experience, including deploying AI workloads in cloud environments.
AI/ML experience beyond GenAI, including model optimization and data preparation.
Education: B. Tech/BE or higher (any graduation/post-graduation acceptable).