AI Developer – Generative AI & LLM Engineer

Test Unity; Bengaluru; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Test Unity in Bengaluru is seeking an experienced AI Developer to build GenAI and LLM-based applications, with hands-on work in Generative AI, LLMs, RAG, AI Agents, and ML.

The role emphasizes end-to-end feature delivery, API integration, and deploying scalable AI solutions, with hybrid work from HSR Layout, Bangalore.

Qualifications

• Hands-on experience with Generative AI, LLMs, and RAG pipelines.
• Experience with API integration and cloud deployment (AWS/Azure).
• Strong knowledge of NLP and model evaluation.

Responsibilities

• Develop and deploy GenAI and LLM-based applications.
• Build RAG-based solutions and AI Agent workflows.
• Integrate AI models with enterprise applications through APIs.
• Optimize AI solutions for performance, accuracy, and scalability.
• Own end-to-end AI feature development.

Skills

Python

AI/ML

Deep Learning

Generative AI

LLMs

Prompt Engineering

RAG pipelines

LangChain

LangGraph

AI Agents

Vector Databases

Embeddings

OpenAI

LLaMA

Mistral

BERT

Claude

Qwen

FastAPI/Flask

REST APIs

SQL databases

NLP

Model Evaluation

Docker

Git

Cloud deployment (AWS/Azure)

Tools

LangChain

LangGraph

AI Agents

Vector Databases

Embeddings

Docker

Git

FastAPI

Flask

REST APIs

SQL databases

AWS

Azure

Job description

AI Developer -- Generative AI & LLM Engineer

Location: HSR Layout, Bangalore

Experience: 3 Years

Work Mode: Hybrid

Role Overview

Looking for an experienced AI Developer with hands‑on expertise in Generative AI, LLMs, RAG, AI Agents, and Machine Learning to build and deploy scalable AI solutions.

Required Skills

• Strong experience in Python, AI/ML, and Deep Learning.
• Hands‑on experience with Generative AI, LLMs, Prompt Engineering, and RAG pipelines.
• Experience with LangChain, LangGraph, AI Agents, Vector Databases, and Embeddings.
• Knowledge of LLM models like OpenAI, LLaMA, Mistral, BERT, Claude, Qwen.
• Experience with FastAPI/Flask, REST APIs, SQL databases.
• Understanding of NLP, Model Evaluation, Docker, Git, and Cloud deployment (AWS/Azure).

Responsibilities

• Develop and deploy GenAI and LLM-based applications.
• Build RAG-based solutions and AI Agent workflows.
• Integrate AI models with enterprise applications through APIs.
• Optimize AI solutions for performance, accuracy, and scalability.
• Own end-to‑end AI feature development.

Preferred: Experience with AI chatbots, automation solutions, enterprise AI projects, and production‑level GenAI applications.