NLP / Agentic AI / Generative AI Engineer

Location: Hyderabad (In-Office) |

Type: Full-Time

Experience: 2-5 Years

### Role Overview

We are looking for an engineer who can build and deploy AI-powered applications using large language models and agentic frameworks. You will be responsible for designing, developing, and shipping intelligent systems that interact with users and automate complex workflows.

### Responsibilities

- Build and deploy AI-powered applications and APIs using LLMs and agentic frameworks

- Design and implement RAG (Retrieval-Augmented Generation) pipelines for knowledge-grounded applications

- Develop robust, production-ready APIs using FastAPI

- Integrate LLMs into product workflows with effective prompt engineering and orchestration

- Evaluate and iterate on AI system outputs for quality, safety, and reliability

- Collaborate with product and engineering teams to ship features end-to-end

### Required Qualifications

- Bachelor's or Master's degree in Computer Science, AI, or a related field

- 2-5 years of experience building and deploying AI or software applications

- Proficiency in a **subset** of the following: LangChain, FastAPI, prompt engineering, RAG architectures, LLM integration and orchestration, API development, building and deploying AI apps to production

- Strong Python programming skills

- Demonstrated ability to take an AI application from prototype to deployment

### Nice to Have

- Experience with cloud platforms (AWS, GCP, or Azure) for hosting and scaling AI applications

- Experience with model fine-tuning, including a theoretical understanding of training procedures, loss functions, and optimization strategies

- Familiarity with evaluation frameworks for LLM-based systems