AI Engineer

About the Role

We are hiring an AI Engineer to design, build, and deploy intelligent systems that power our client products and internal AI tools. You will work on LLM integrations, RAG pipelines, fine-tuned model deployments, and custom NLP workflows. Our AI stack includes OpenAI, Groq, Anthropic, Hugging Face, and Pinecone. You will take abstract business requirements and architect reliable, cost-effective AI solutions that actually work in production.

Tech Stack

Requirements

• M.Tech, B.Tech in CS/AI/ML or equivalent professional AI engineering experience.
• Strong Python proficiency with experience in async and production-grade code.
• Hands-on experience with LLM APIs (OpenAI GPT-4, Groq Llama, Claude).
• Understanding of Retrieval-Augmented Generation (RAG) architectures and vector databases.
• Familiarity with LangChain or LlamaIndex for building AI agent and pipeline systems.
• Experience with fine-tuning and evaluating transformer-based language models.
• Ability to deploy AI models as APIs using FastAPI or Flask.

Responsibilities

• Design and implement RAG pipelines for document Q&A and knowledge base applications.
• Integrate multi-model LLM fallback chains optimized for cost, speed, and accuracy.
• Build AI agent systems for task automation, data extraction, and decision making.
• Fine-tune and evaluate open-source models (Llama 3, Mistral) for specific client use cases.
• Optimize prompt engineering, context management, and token cost efficiency.
• Deploy AI inference services as production-ready APIs with rate limiting and logging.
• Research and implement the latest AI techniques to continuously improve system quality.