Python Backend - GenAI Engineer

Optimum Solutions; Chennai; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Optimum Solutions is seeking an experienced Python Backend / AI Engineer in Chennai for hands-on backend development and GenAI projects. The role focuses on building scalable Python services, LLM integrations, RAG-powered workflows, and secure AI applications.

You will design RESTful APIs, work with PostgreSQL/MySQL, and collaborate with client teams to deliver AI-enabled solutions. Immediate joiners preferred; work location is Chennai with on-site requirements.

Qualifications

• 7-12 years of experience in backend/AI roles.
• Strong Python and Fast API expertise.
• Hands-on GenAI/LLM integration and RAG deployments.
• Experience designing REST APIs and database schemas.
• Familiarity with LangChain/LangGraph frameworks.
• Prominent version control with Git.

Responsibilities

• Design and develop scalable backend services using Python/FastAPI.
• Build and integrate GenAI/LLM-powered applications.
• Develop RAG-based AI workflows and agents where needed.
• Create REST APIs and database integrations.
• Implement logging, monitoring, and security for AI apps.
• Collaborate with teams and clients to deliver AI solutions.

Skills

Python

Fast API

REST API

GenAI / LLM API integration

RAG solutions

LangChain / LangGraph

Prompt engineering

Git

Scalable backend development

Tools

PostgreSQL

MySQL

Docker

Job description

Work Type: Work from Office Mandatory, Monday to Friday

Work Timing: 9:00 AM to 6:00 PM

Work Location: Chennai Ramanujam IT Tech Park, Thiruvanmiyur and/or Client Office Premises

Notice Period: Immediate Joiners preferred; maximum 30 days

Experience: 7-12 Years

Role:

We are looking for an experienced Python Backend / AI Engineer with strong expertise in Python-based backend development and hands-on experience in Generative AI, LLM integration, RAG, and AI application development.

Key Responsibilities:

• Design and develop scalable backend services using Python/Fast API.
• Build and integrate GenAI/LLM-powered applications.
• Develop RAG-based solutions and AI-driven workflows.
• Design and integrate REST APIs and databases.
• Develop AI Agents and Multi-Agent solutions where required.
• Implement logging, monitoring, evaluation, and tracing for AI applications.
• Ensure application security, authorization, performance, and cost efficiency.
• Collaborate with technical teams and client stakeholders to deliver AI solutions.

Must Have:

• Strong experience in Python and Fast API
• REST API design and development
• Hands-on experience with PostgreSQL or MySQL
• GenAI / LLM API integration
• Experience implementing RAG solutions
• Experience with LangChain, LangGraph, or similar frameworks
• Basic prompt engineering / prompt design
• Strong development experience using Git
• Experience in developing scalable backend applications

Good to Have:

• Experience with Azure OpenAI / Azure AI Search
• Application development on AWS or Azure
• Hands-on experience with Docker
• Experience in AI Agent / Multi-Agent development
• Asynchronous processing and streaming
• Experience with AI application deployment and integration

Ability to Learn & Adopt:

• Evaluation, logging, monitoring, and tracing of AI applications
• AI Ops and identification of accuracy degradation or abnormal AI behaviour
• Understanding of AI security, authorization, and access control
• AI application cost monitoring and optimization
• Ability to quickly learn and adopt new AI/Cloud technologies
• Strong problem-solving and analytical skills