Backend Engineer – Python/Generative AI

Winzons; India; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

EXL Service is seeking a Backend Engineer with 5–8 years of experience to design, develop, and maintain scalable backend services using Python. The role focuses on Generative AI, LLM-based enterprise solutions, and cloud-native architectures, collaborating with cross-functional teams to deliver innovative business solutions.

You will work on building RESTful APIs, GraphQL APIs, and LangChain/LangGraph workflows, leveraging AWS DynamoDB and S3 for data management and implementing observability

Qualifications

• 5 to 8 years of experience in backend software development.
• Strong expertise in Python backend development.
• Hands-on experience with Flask and/or FastAPI.
• Strong understanding of REST APIs, backend architecture, and microservices.
• Experience with GraphQL and AWS AppSync.
• Hands-on experience building LLM and Generative AI applications.
• Experience with LangChain and LangGraph for orchestration and workflow management.
• Experience with Langfuse for LLM observability, tracing, and monitoring.
• Strong understanding of agentic workflows and stateful AI systems.
• Hands-on experience with AWS services, including DynamoDB and S3.
• Good understanding of system design, scalability, and distributed architectures.
• Experience writing unit tests using Pytest.
• Strong knowledge of Git, version control, and code review practices.

Responsibilities

• Design, develop, and maintain scalable backend applications and APIs using Python.
• Build and optimize RESTful APIs and backend services for enterprise-grade applications.
• Design and implement LLM/GenAI-based use cases and agentic workflows.
• Develop and maintain LangChain and LangGraph-based orchestration workflows for AI systems.
• Work on GraphQL APIs and AWS AppSync integrations.
• Implement observability, tracing, and monitoring for LLM applications using Langfuse.
• Leverage AWS services such as DynamoDB and S3 for scalable storage and data management.
• Participate in architecture and system design discussions to build scalable, secure, and production-ready systems.
• Write clean, maintainable, and testable code with appropriate unit test coverage.
• Troubleshoot, debug, and optimize application performance.
• Collaborate with product, engineering, and business stakeholders to translate requirements into scalable technical solutions.
• Participate in code reviews and adhere to engineering best practices and development standards.

Skills

Python

Flask

FastAPI

REST APIs

GraphQL

AWS AppSync

LangChain

LangGraph

Langfuse

AWS DynamoDB

AWS S3

Pytest

Git

Tools

GraphQL

Job description

Company Name: EXL Service

Job Role: Backend Engineer

Experience Required: 5 to 8 Years

Location: Delhi NCR Bangalore Pune Gurgaon/Gurugram, India

Industry: Artificial Intelligence / Data Analytics / Software Development

Work Focus: Generative AI, LLM Systems, Backend Engineering

About the Role :

We are seeking a highly skilled Backend Engineer with strong expertise in Python development and experience building Generative AI and Large Language Model (LLM)-based enterprise solutions. The ideal candidate will be responsible for designing, developing, and maintaining scalable backend services, integrating AI-driven applications, and contributing to the architecture of production-grade systems. This role offers the opportunity to work on cutting-edge AI technologies, agentic workflows, and cloud-native architectures while collaborating with cross-functional teams to deliver innovative business solutions.

Key Responsibilities :

• Design, develop, and maintain scalable backend applications and APIs using Python.


• Build and optimize RESTful APIs and backend services for enterprise-grade applications.


• Design and implement LLM/GenAI-based use cases and agentic workflows.


• Develop and maintain LangChain and LangGraph-based orchestration workflows for AI systems.


• Work on GraphQL APIs and AWS AppSync integrations.


• Implement observability, tracing, and monitoring for LLM applications using Langfuse.


• Leverage AWS services such as DynamoDB and S3 for scalable storage and data management.


• Participate in architecture and system design discussions to build scalable, secure, and production-ready systems.


• Write clean, maintainable, and testable code with appropriate unit test coverage.


• Troubleshoot, debug, and optimize application performance.


• Collaborate with product, engineering, and business stakeholders to translate requirements into scalable technical solutions.


• Participate in code reviews and adhere to engineering best practices and development standards.

Required Skills & Experience :

• 5 to 8 years of experience in backend software development.


• Strong expertise in Python backend development.


• Hands-on experience with Flask and/or FastAPI.


• Strong understanding of REST APIs, backend architecture, and microservices.


• Experience with GraphQL and AWS AppSync.


• Hands-on experience building LLM and Generative AI applications.


• Experience with LangChain and LangGraph for orchestration and workflow management.


• Experience with Langfuse for LLM observability, tracing, and monitoring.


• Strong understanding of agentic workflows and stateful AI systems.


• Hands-on experience with AWS services, including DynamoDB and S3.


• Good understanding of system design, scalability, and distributed architectures.


• Experience writing unit tests using Pytest.


• Strong knowledge of Git, version control, and code review practices.


• Excellent debugging, analytical, and problem-solving skills.

Preferred Qualifications :

• Experience deploying and managing AI applications in production environments.


• Exposure to cloud-native architectures and containerized deployments.


• Familiarity with CI/CD pipelines and DevOps practices.


• Experience working in Agile development environments.

Why Join Us? :

• Work on cutting-edge Generative AI and Agentic AI solutions.


• Build scalable enterprise-grade applications used by global clients.


• Collaborate with highly skilled engineering and AI teams.


• Opportunity to influence architecture, innovation, and product direction.