Job Title : LLM Engineer
Experience : 5+ Years (Relevant : 46 Years)
Location : Gurgaon
Looking for Immediate Joiners only.
About the Role :
We are seeking a highly skilled and experienced LLM Engineer to join our cutting-edge GenAI team. The ideal candidate will have a strong background in Python, Prompt Engineering, Agentic AI, and frameworks like LangGraph. You will play a key role in developing, deploying, and optimizing Large Language Model (LLM)-based applications, agents, and pipelines to solve real-world problems and drive innovation in intelligent systems.
Key Responsibilities :
- Design, build, and deploy scalable applications using Large Language Models (LLMs).
- Develop intelligent agents using LangGraph and other agentic AI techniques.
- Create and optimize prompts to improve LLM task performance across multiple domains.
- Collaborate with cross-functional teams including data scientists, ML engineers, and product managers to integrate GenAI solutions into products.
- Fine-tune and evaluate LLMs for domain-specific tasks and use cases.
- Contribute to building internal tools, libraries, and reusable components for GenAI development.
- Monitor, evaluate, and continuously improve system performance, accuracy, and safety.
Required Skills & Experience :
46 years of hands-on experience in building and deploying GenAI / LLM-based solutions.Strong proficiency in Python and associated libraries for NLP and LLMs (e.g., LangChain, Transformers, LangGraph).Deep understanding of Prompt Engineering and its application in production systems.Experience building Agentic AI systems and workflow-driven intelligent applications.Solid understanding of LLMs (e.g., GPT, LLaMA, Claude) and their Familiarity with model evaluation metrics and ethical considerations around LLM use.Strong problem-solving skills, communication, and the ability to work in an agile environment.Preferred Qualifications :
Experience working with vector databases (e.g., FAISS, Pinecone).Exposure to knowledge retrieval (RAG), few-shot learning, or fine-tuning.Contributions to open-source GenAI projects or frameworks.Experience deploying LLMs at scale on cloud platforms (AWS, GCP, Azure).(ref : hirist.tech)