We are looking for an experienced Prompt Engineer to design, optimize, and deploy enterprise-grade Generative AI solutions powered by Large Language Models (LLMs). The ideal candidate should have strong expertise in Prompt Engineering, Retrieval-Augmented Generation (RAG), Agentic AI, LLM orchestration, and AI application development, with the ability to build reliable, scalable, and production-ready AI solutions.

Key Responsibilities :

- Design, evaluate, and optimize prompts for enterprise AI applications using state-of-the-art Large Language Models (LLMs).

- Build and implement RAG (Retrieval-Augmented Generation) pipelines to improve the accuracy and relevance of AI-generated responses.

- Develop and deploy Agentic AI workflows capable of autonomous task execution and multi-step reasoning.

- Collaborate with Product, Data Science, Engineering, and Business teams to translate business requirements into AI-powered solutions.

- Integrate LLMs with enterprise applications using APIs, vector databases, and orchestration frameworks.

- Evaluate AI model performance and continuously improve prompt quality, response accuracy, latency, and cost efficiency.

- Develop automated testing, evaluation, and guardrail frameworks for prompt validation and model quality.

- Work with Data Engineering teams to build knowledge bases, document ingestion pipelines, and embedding workflows.

- Implement responsible AI practices, including security, governance, and prompt safety.

- Stay updated with the latest advancements in Generative AI, LLMs, and AI engineering frameworks.

Required Skills :

- 10-15 years of experience in Software Engineering, AI/ML, or Data Engineering, with significant experience in Generative AI.

- Strong expertise in Prompt Engineering, LLMs, RAG, and Agentic AI.

- Proficiency in Python (preferred) or Java.

- Hands-on experience with LangChain, LlamaIndex, Semantic Kernel, LangGraph, or similar orchestration frameworks.

- Experience with commercial and open-source LLMs such as OpenAI GPT, Claude, Gemini, Llama, or Mistral.

- Experience with vector databases such as Pinecone, Weaviate, Milvus, ChromaDB, or FAISS.

- Knowledge of deep learning frameworks such as TensorFlow or PyTorch.

- Strong understanding of Natural Language Processing (NLP) techniques and transformer architectures.

- Experience deploying AI applications on AWS, Azure, or GCP.

- Strong problem-solving, analytical, and stakeholder management skills.