Gen AI Engineer

EdgeVerve Systems; Pune District, Chennai District, Bengaluru; Hybrid; INR 1,500,000 - 2,400,000; Full time

Job summary

EdgeVerve Systems in Pune, India, is seeking a backend AI engineer to build and scale GenAI-powered services. You will design APIs, integrate LLMs, vector databases, and enterprise systems, and develop production-grade AI models for real-world use cases.

You will work with Python frameworks, Docker/Kubernetes, and a modern microservices stack to deliver scalable, observable AI solutions. This role requires hands-on GenAI experience and strong backend capabilities.

Qualifications

• Strong experience in Python-based backend development.
• Hands-on work with GenAI, RAG, Agentic AI, and AI Assistant implementations.
• Experience with LLMs, vector databases, and prompt engineering.
• Knowledge of microservices architecture and containerized deployments.

Responsibilities

• Develop AI Next platform services and product features.
• Build and enhance GenAI, RAG, Agentic AI, and AI Assistant capabilities.
• Design, develop, and maintain REST APIs and microservices.
• Integrate LLMs, vector databases, and enterprise systems.
• Develop AI models and train models for business use cases.
• Identify use cases leveraging ChatGPT/OpenAI technologies.
• Implement testing, monitoring, and observability for AI apps.
• Develop scalable backend services using Python frameworks.
• Collaborate with cross-functional teams to deliver AI-powered solutions.
• Deploy and manage apps using containers and orchestration platforms.

Skills

Python

FastAPI/Flask

REST APIs

PostgreSQL

GenAI & RAG

Prompt Engineering

Docker & Kubernetes

Vector Databases

Tools

Docker

Kubernetes

Job description

Role Overview

Develop AI Next platform services and product features by building GenAI, RAG, Agentic AI, and AI Assistant capabilities. Design and develop APIs and microservices, integrate LLMs, vector databases, and enterprise systems, and implement testing, monitoring, and observability. The role also involves AI model development, building and training models for specific business use cases, and leveraging LLM technologies such as ChatGPT/OpenAI to create GenAI solutions through prompt engineering and related capabilities.

Key Responsibilities

• Develop AI Next platform services and product features.
• Build and enhance GenAI, RAG (Retrieval-Augmented Generation), Agentic AI, and AI Assistant capabilities.
• Design, develop, and maintain REST APIs and microservices.
• Integrate LLMs, vector databases, and enterprise applications/systems.
• Develop AI models and train models for specific business purposes and use cases.
• Identify and implement use cases that can leverage LLM technologies such as ChatGPT/OpenAI.
• Build capabilities around Prompt Engineering and Generative AI.
• Implement testing, monitoring, logging, and observability for AI applications and services.
• Develop scalable and secure backend services using Python frameworks.
• Collaborate with cross-functional teams to deliver AI-powered solutions.
• Deploy and manage applications using containerization and orchestration platforms.

Required Skills

Python, Fast API / Flask, REST APIs, PostgreSQL, GenAI & RAG,Prompt , Engineering ,Docker & Kubernetes, Vector Databases.

Preferred Candidate Profile

• Strong experience in Python-based backend development.
• Hands-on experience with GenAI, RAG, Agentic AI, and AI Assistant implementations.
• Experience working with LLMs, vector databases, and prompt engineering.
• Knowledge of Docker, Kubernetes, and microservices architecture.
• Experience building and training AI models for domain-specific use cases.
• Ability to design and develop scalable, production-grade AI solutions.