AI - Engineer

Overview

AI Engineer responsible for designing, building, and deploying LLM- and Generative AI-powered applications. The role combines prompt engineering, RAG, agentic workflows, model evaluation, and Java/Python backend development.

What you'll do

• Design and deploy LLM applications, including chatbots, copilots, agents, and RAG systems.
• Develop prompt engineering strategies for production use cases.
• Build RAG pipelines using embeddings, chunking, and vector databases.
• Fine-tune and evaluate open-source and closed-source LLMs.
• Implement agentic workflows with orchestration frameworks.
• Build Java and Python backend services and APIs for LLM applications.
• Monitor deployed systems for performance, safety, drift, and degradation.

What you'll need

• Bachelor's or Master's degree in Computer Science, Machine Learning, or a related field, or equivalent practical experience.
• Strong programming skills in Java and Python.
• Hands-on experience with LLM APIs and open-source LLMs.
• Practical experience with prompt engineering and RAG architecture.
• Experience with vector databases and embedding models.
• Familiarity with LLM orchestration frameworks such as LangChain, LangGraph, or LlamaIndex.
• Experience with REST or gRPC APIs, cloud platforms, Docker, and Kubernetes.

Nice to have

• Experience fine-tuning LLMs with LoRA, QLoRA, or PEFT.
• Experience designing multi-agent or tool-using AI workflows.
• Familiarity with LLM evaluation and safety tooling.
• Working knowledge of React for LLM-driven features.
• Experience with MLOps or LLMOps practices.
• Background in NLP or open-source LLM/Generative AI contributions.

Details

• Location: Noida, Uttar Pradesh, India.