Lead Python developer - OnSite (Kochi)

VGreen Technology Solutions (VGreenTEK); Coimbatore District; On-site; INR 2,200,000 - 2,400,000; Full time

Job summary

VGreen Technology Solutions (VGreenTEK) in Kochi is seeking a Lead Python Developer with hands-on Generative AI and LLM experience to design, build, and deploy production-grade AI systems.

You will design and deploy LLM-powered apps, build conversational agents and multi-agent workflows, architect RAG pipelines, and develop scalable Python backends using FastAPI, vector stores, and AWS services. Collaborate with product teams to deliver enterprise GenAI solutions in a cloud-native environment.

Qualifications

• Proven experience with Generative AI and LLM development.
• Hands-on work with LangChain, LangGraph, OpenAI Agents or CrewAI.
• Strong Python engineering with microservices background.
• Ability to design end-to-end GenAI architectures.
• AWS/cloud deployment experience is preferred.

Responsibilities

• Designing and deploying LLM-powered applications (GPT, Claude, Llama, Mistral).
• Building conversational agents, copilots, and multi-agent workflows.
• Architecting RAG pipelines, prompts, and tool calling.
• Developing scalable Python backends (FastAPI, async APIs, vector DB integrations).
• Deploying solutions on AWS (Lambda, ECS/EKS, Bedrock, SageMaker, CI/CD).
• Collaborating with product and engineering teams to deliver enterprise GenAI solutions.

Skills

Generative AI

LLM development

Python

Microservices

End-to-end GenAI

AWS deployment

Tools

LangChain

LangGraph

OpenAI Agents

CrewAI

FastAPI

Vector DB

Job description

Location: Kochi

Notice: Immediate to 15 days.

Budget: 22 to 24 LPA

Experience: 7 Years

Role Overview

We are looking for a Lead Python Developer with strong hands-on experience in Generative AI and LLM-based solutions to design, build, and deploy production-grade AI systems.

What the Role Will Focus On

• Designing and deploying LLM-powered applications (GPT, Claude, Llama, Mistral)
• Building conversational agents, copilots, and multi-agent workflows
• Architecting RAG pipelines, prompt strategies, and tool/function calling
• Developing scalable Python backends (FastAPI, async APIs, vector database integrations)
• Deploying solutions on AWS (Lambda, ECS/EKS, Bedrock, SageMaker, CI/CD pipelines)
• Collaborating with product and engineering teams to deliver enterprise-ready GenAI solutions

Required Skills & Experience

• Strong hands-on experience with Generative AI and LLM development
• Experience with LangChain, LangGraph, OpenAI Agents, CrewAI, or similar frameworks
• Solid Python engineering skills with microservices experience
• Proven ability to design end-to-end GenAI architectures
• Cloud-native deployment experience (AWS preferred)

Nice to Have

• Experience with multimodal AI (text, image, audio)
• Knowledge of knowledge graphs
• Experience with enterprise system integrations