AI/ML Intern

Build FastAPI endpoints that integrate LLMs in a seamless inference pipeline.
Apply prompt engineering techniques to optimize different LLM-based applications. Work with advanced frameworks like LangChain, LangGraph, Hugging Face, OpenAI, and others for model inference and orchestration. Develop tools and implement tool calling techniques to enhance LLM capabilities. Use Pydantic models to enforce structure and parse LLM responses effectively. Leverage object-oriented programming (OOP) principles to write scalable and reusable code. Contribute to internal documentation and actively share findings, utilities, and best practices. Stay updated with the latest AI research and tooling, integrating innovations into real-world systems.","requirements":" Must be a B.Tech Graduate of 2026 batch. Strong experience in Python for AI/ML development and backend systems. Practical knowledge in prompt engineering and LLM optimization for real-world use cases. Proficiency with LangChain, LangGraph, Hugging Face Transformers, and Datasets libraries. Background in AI/ML research or academic projects, with hands-on model experimentation. Solid grasp of Object-Oriented Programming (OOP) and strong problem-solving abilities. Ability to work independently as well as within a collaborative team environment. Strong communication and documentation skills to convey complex ideas effectively.","perks":" Hands-on experience with real-world AI deployments. Work with state-of-the-art AI tools and platforms. Mentorship from top AI engineers and researchers. Flexible, innovation-driven work culture.","