AI Engineer (LLMs & Generative AI) - Gurugram, India

Position: AI Engineer (LLMs & Generative AI)

Experience: 12 Years (Full-Time)

Location: Gurugram, Gurgaon, India (Work From Office - 5 Days a Week)

Overview

CoolBoots is seeking a motivated AI Engineer with 12 years of hands-on experience in building and deploying LLM-powered applications. This role involves significant work on model fine-tuning, Retrieval-Augmented Generation (RAG) systems, and AI agent frameworks to develop scalable, real-world AI products. You will collaborate closely with engineering and product teams, contributing to experimentation, development, and optimization processes.

Key Responsibilities

• Design, build, and optimize LLM-based applications using frameworks such as Hugging Face, OpenAI APIs, LangChain, or similar.
• Develop and maintain RAG pipelines, encompassing embeddings generation, vector databases, retrieval strategies, and prompt orchestration.
• Fine-tune and adapt language models for specific use cases, ensuring a balance between performance, cost, and latency.
• Implement robust model evaluation, monitoring, and optimization strategies using well-defined quality and performance metrics.
• Build and experiment with advanced AI agent frameworks (e.g., LangGraph, CrewAI, AutoGen, AgentKit) to enable multi-step reasoning and complex workflows.
• Collaborate effectively with cross-functional teams to translate product requirements into innovative AI solutions.
• Stay abreast of the latest advancements in LLMs, GenAI tooling, and best practices, and proactively apply them to ongoing projects.

Required Skills & Qualifications

• Strong foundation in Machine Learning, Natural Language Processing (NLP), and Python programming.
• Practical experience with PyTorch, Hugging Face Transformers, and modern LLM workflows.
• Hands-on experience building applications using OpenAI or similar LLM platforms.
• Proven experience working with LangChain (or equivalent frameworks) and various vector databases (e.g., FAISS, Pinecone, Weaviate, Chroma).
• Demonstrated ability to take ML/AI projects from initial experimentation through to production-ready prototypes.
• 12 years of professional or equivalent hands-on experience, including strong personal or open-source projects in NLP/LLMs.

Nice To Have

• Exposure to deployment workflows, including APIs, Docker, and cloud platforms.
• Experience with prompt engineering, LLM evaluation frameworks, or observability tools for LLMs.
• Familiarity with cost optimization and latency tuning techniques for LLM-based systems.

Ideal Candidate Profile

You are a curious, proactive, and passionate individual dedicated to generative AI. You enjoy experimenting, learning quickly, and building practical, impactful solutions with LLMs. You are comfortable taking ownership of features and thrive in a fast-paced environment focused on delivering real-world AI products.