Job
Description
We're looking for an AI Engineer with a passion for building intelligent, high-impact AI products on top of Large Language Models (LLMs). In this role, you'll play a key part in developing generative AI applications and intelligent agent workflows that go beyond traditional search or support bots - these are systems designed to reason, adapt, and learn. You'll work closely with product and engineering teams to build LLM-powered solutions using the most suitable LLM techniques - be it RAG, fine-tuning, RLHF, prompt chaining, or agentic workflows like Pandas Agent. We value innovation, adaptability, and a strong understanding of the LLM ecosystem. This role is central to our Generative AI charter, but the scope extends beyond language, into any space where LLMs can bring transformative value. Responsibilities Design and implement scalable GenAI applications powered by LLMs and other foundational models. Choose the right approach for each problem - whether that's Retrieval-Augmented Generation (RAG), fine-tuning, model compression, agentic workflows, or reinforcement learning. Build backend systems and APIs that integrate LLMs into real-world use cases. Develop custom agents that can autonomously perform complex tasks across documents, tools, or datasets. Stay up to date with the latest LLM research, trends, tools, and papers - and bring those insights into production. Collaborate cross-functionally to build AI-native features into core products. Drive continuous improvement through evaluation, monitoring, and feedback loops across your solutions. Explore multimodal or non-language use cases of GenAI as the organization expands its charter. Requirements 3+ years of experience in ML/AI settings building production-scale systems. Deep understanding of LLMs and NLP concepts, with proven ability to apply them in real-world scenarios. Experience with LLM techniques like prompt engineering, RAG, agentic frameworks, or model fine-tuning. Strong programming skills (Python or equivalent). Ability to build and deploy production-grade APIs and systems that can scale. Passion for keeping up with the rapidly evolving AI landscape and applying new knowledge to practical problems. Good-to-Have Familiarity with vector stores and embedding models. Experience building agents using LangChain, LlamaIndex, or custom orchestration logic. Exposure to cloud platforms (AWS/GCP/Azure) and relevant AI services. Understanding of CI/CD workflows, observability, and performance optimization. This job was posted by Abhishek Shome from WinZO. Show more Show less
