Generative AI Developer

Tata Consultancy Services; Chennai District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Tata Consultancy Services in Chennai is hiring a Gen AI Developer with 4-15 years of experience. The role focuses on building and optimizing GenAI applications, including LLM-powered services, embeddings, and NLP fundamentals.

The candidate will engineer prompts, design RAG solutions, evaluate model and agent performance, and deploy scalable GenAI systems on cloud platforms with CI/CD and monitoring in place.

Qualifications

• Strong knowledge of GenAI concepts including foundation models and NLP fundamentals.
• Experience designing and deploying LLM-powered services for real business use-cases.
• Hands-on prompt engineering and evaluation of output quality.
• Experience building RAG solutions and retrieval strategies.
• Experience with cloud platforms for scalable GenAI deployments.

Responsibilities

• Design, implement, and optimize GenAI applications with focus on accuracy and scalability.
• Develop prompt templates and evaluate prompts to improve results.
• Build Retrieval-Augmented Generation solutions and integrate retrieval strategies.
• Assess model and agent performance using evaluation benchmarks.
• Work with cloud-based GenAI platforms and ensure high availability.
• Follow MLOps/LLMOps practices: CI/CD, monitoring, and version control.

Skills

Gen AI concepts

Prompt engineering

RAG architectures

LLMs & embeddings

Cloud platforms (AWS/Azure/GCP)

MLOps / LLMOps

Python

Java/.Net

Model evaluation & benchmarking

Job description

Tata Consultancy Services is Hiring Gen AI Developer for Chennai Location

Experience: 4-15 years

Mode of Interview: Walk-in

Job Description

• Strong knowledge of Generative AI concepts including foundation models / LLMs, embeddings, and NLP fundamentals used in GenAI solutions.
• Design, implement, and optimize GenAI applications (LLM-powered services) for real business use-cases, with focus on accuracy, efficiency, and scalability.
• Hands-on prompt engineering (e.g., zero/few-shot, Chain-of-Thought, Tree-of-Thought, prompt templates) and ability to evaluate and refine prompts based on output quality.
• Build Retrieval-Augmented Generation (RAG) solutions, including retrieval strategy integration and prompt + retrieval orchestration patterns.
• Experience with agent / app evaluation practices—evaluate model and agent performance for GenAI use-cases (quality, effectiveness, benchmarking).
• Cloud-based GenAI platform experience (e.g., AWS / Azure / GCP) for building and deploying scalable GenAI solutions with high availability and performance.
• MLOps / LLMOps-aligned practices: CI/CD, monitoring, logging, and version control for deploying and operating GenAI systems in production.
• Proficiency in programming languages such as Python, .Net or Java, with experience in relevant libraries and frameworks (e.g., TensorFlow, PyTorch, Keras).