SDE AI Engineer Generative AI AWS Bedrock RAG Python

Quess; Hyderabad, Pune District, Bengaluru; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Quess in Hyderabad, Telangana is seeking a backend engineer to design scalable GenAI-powered services. You will build production-grade AI applications with Python, FastAPI, and AWS, focusing on RAG, LLM integration and secure cloud-native architectures.

You will collaborate with AI/ML teams, implement CI/CD pipelines, and ensure robust, scalable deployments using Docker, Kubernetes, and Bedrock services. BS in CS or related field required.

Qualifications

• 4+ years of software development / SDE experience
• Strong Python programming
• Generative AI / GenAI experience
• LLM / Large Language Models experience
• RAG / Retrieval-Augmented Generation experience
• Amazon AWS Bedrock experience
• LangChain experience
• REST APIs / FastAPI
• AWS cloud services
• Microservices / Serverless architecture
• Docker
• Kubernetes
• Git / Version Control
• CI/CD

Responsibilities

• Design and develop scalable backend applications using Python and FastAPI.
• Build and deploy production-grade Generative AI and LLM applications.
• Develop Retrieval-Augmented Generation (RAG) pipelines for enterprise AI use cases.
• Integrate Amazon Bedrock foundation models into applications and AI workflows.
• Implement LangChain/LangGraph based LLM workflows and AI applications.
• Work with embeddings, semantic search and vector databases.
• Design and implement microservices and serverless architectures using AWS.
• Develop solutions using AWS services such as S3, Lambda, API Gateway, RDS and Step Functions.
• Build and manage containerized applications using Docker and Kubernetes.
• Work with Red Hat OpenShift Service on AWS (ROSA) where required.
• Design and maintain CI/CD pipelines using Jenkins, GitLab or AWS CodePipeline.
• Troubleshoot, optimize and maintain cloud-native applications across development and production environments.
• Implement secure and scalable AI applications using IAM, networking and cloud security practices.
• Apply prompt engineering, model integration, response validation and AI safety techniques.
• Explore and implement AI capabilities including AI Agents, AWS AgentCore and MCP.
• Leverage AI-assisted development tools such as Kiro, GitHub Copilot and Claude.
• Collaborate with engineering, product and AI/ML teams to deliver production-quality solutions.

Skills

Python

Generative AI / GenAI

LLM / Large Language Models

RAG / Retrieval-Augmented Generation

LangChain

REST APIs / FastAPI

AWS cloud services

Docker

Kubernetes

Git / Version Control

CI/CD

Education

Bachelor's degree in Computer Science, Engineering, Information Systems or a related discipline

Tools

AWS Bedrock

LangGraph

Jenkins

GitLab CI

AWS CodePipeline

OpenShift / ROSA

Job description

Key Responsibilities

• Design and develop scalable backend applications using Python and modern frameworks such as FastAPI.
• Build and deploy production-grade Generative AI and LLM applications.
• Develop Retrieval-Augmented Generation (RAG) pipelines for enterprise AI use cases.
• Integrate Amazon Bedrock foundation models into applications and AI workflows.
• Implement LangChain/LangGraph based LLM workflows and AI applications.
• Work with embeddings, semantic search and vector databases.
• Design and implement microservices and serverless architectures using AWS.
• Develop solutions using AWS services such as S3, Lambda, API Gateway, RDS and Step Functions.
• Build and manage containerized applications using Docker and Kubernetes.
• Work with Red Hat OpenShift Service on AWS (ROSA) where required.
• Design and maintain CI/CD pipelines using Jenkins, GitLab or AWS CodePipeline.
• Troubleshoot, optimize and maintain cloud-native applications across development and production environments.
• Implement secure and scalable AI applications using appropriate IAM, networking and cloud security practices.
• Apply prompt engineering, model integration, response validation and AI safety techniques.
• Explore and implement modern AI capabilities including AI Agents, AWS AgentCore and Model Context Protocol (MCP).
• Leverage AI-assisted development tools such as Kiro, GitHub Copilot and Claude to improve coding, testing, debugging and documentation.
• Collaborate with engineering, product and AI/ML teams to deliver production-quality solutions.

Mandatory Skills

• 4+ years of software development / SDE experience
• Strong Python programming
• Generative AI / GenAI
• LLM / Large Language Models
• RAG / Retrieval-Augmented Generation
• Amazon AWS Bedrock
• LangChain
• REST APIs / FastAPI
• AWS cloud services
• Microservices / Serverless architecture
• Docker
• Kubernetes
• Git / Version Control
• CI/CD

Good to Have

• AWS AgentCore
• Model Context Protocol (MCP)
• LangGraph
• AI Agents / Agentic AI
• Kiro
• GitHub Copilot
• Claude
• AWS S3, Lambda, API Gateway, RDS, Step Functions
• CloudFormation
• Jenkins / GitLab CI / AWS CodePipeline
• Red Hat OpenShift / ROSA
• Vector databases such as Pinecone, FAISS, Chroma
• Embeddings and semantic search
• AWS IAM, networking and security
• AWS Certified Solutions Architect / Developer

Candidate Profile

• Strong backend software engineering mindset with hands-on development experience.
• Proven experience building production GenAI/LLM applications, not just POCs or theoretical AI projects.
• Strong understanding of RAG architecture, LLM integration and prompt engineering.
• Experience deploying applications on AWS and working with cloud-native architectures.
• Strong debugging, analytical and problem-solving skills.
• Ability to write clean, maintainable and production-quality code.
• Good communication and collaboration skills.
• Bachelor's degree in Computer Science, Engineering, Information Systems or a related discipline.