Generative AI Engineer - Prompt Engineering

Job Title : Generative AI Engineer (LLMs, Prompt Engineering)

Experience : 14 Years

Location : Mumbai / Pune (On-site or Hybrid as per policy)

Job Type : Full-Time

Notice Period : 30 Days

Job Summary

We are seeking a talented Generative AI Engineer with experience in working with Large Language Models (LLMs) and Prompt Engineering to join our growing AI/ML team. You will be responsible for designing, fine-tuning, and optimizing AI models for real-world applications such as content generation, conversational AI, summarization, code generation, and more. If youre passionate about cutting-edge AI technologies and want to build intelligent systems that create meaningful impact, this role is for you.

Key Responsibilities

• Develop, fine-tune, and optimize Generative AI models, especially Large Language Models (LLMs) like GPT, LLaMA, Claude, Mistral, or similar.
• Design, experiment with, and refine prompts for various LLM-based use cases (e.g., chatbots, summarization, document Q&A, content generation).
• Evaluate model performance through benchmarks, A/B testing, and human-in-the-loop feedback mechanisms.
• Integrate LLMs with internal tools and external APIs to enable scalable real-world applications.
• Collaborate with product managers, data scientists, and engineers to build, test, and deploy AI-powered features.
• Research emerging trends in generative AI, including open-source models, retrieval-augmented generation (RAG), multi-modal systems, etc.
• Maintain best practices in data handling, model evaluation, prompt libraries, and documentation.
• Contribute to internal knowledge-sharing sessions on prompt tuning, model behavior, and model hallucination mitigation.
  
  

• Bachelors or Masters degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
• 14 years of hands-on experience in AI/ML/NLP, with at least 1 year specifically in LLMs or Generative AI.
• Proficiency with Python and popular ML libraries such as PyTorch, TensorFlow, Hugging Face Transformers, LangChain, OpenAI APIs, etc.
• Experience in designing and optimizing prompts for LLMs to achieve specific outputs or tasks.
• Strong understanding of model behavior, prompt tuning, and techniques for reducing hallucinations.
• Familiarity with vector databases (e.g., Pinecone, FAISS, Weaviate) and concepts like semantic search or RAG pipelines.
• Good understanding of RESTful APIs and deployment workflows using Docker, FastAPI, or Flask.
  
  

• Experience with fine-tuning open-source LLMs (e.g., LLaMA, Mistral, Falcon).
• Familiarity with tools like LangChain, LlamaIndex, Haystack, or similar frameworks for building LLM pipelines.
• Knowledge of multi-modal AI (text + image), voice assistants, or embedding techniques.
• Published projects or GitHub repos showcasing LLM use cases or prompt engineering work.
  
  

• Work on cutting-edge AI applications using the latest in Generative AI and LLM technologies.
• Be part of an innovative and collaborative tech team.
• Opportunity to contribute to high-impact AI products in a rapidly evolving field.