Description

You will design, develop, and maintain complex software solutions for AI/ML and Generative AI systems, ensuring high maintainability, testability, and compliance.

This role is hybrid.

Responsibilities

• Design and implement scalable application architectures and interfaces using Python, Scala, or Java.
• Build and deploy GenAI inference platforms using vLLM or Triton Inference Server within containerized environments.
• Develop automated test suites (integration, regression, performance) and CI/CD pipelines to ensure code quality.
• Implement RAG processes including chunking, embedding, retrieval, reranking, and summarization for various use cases.
• Mentor engineers on CI/CD practices, automation tool stacks, and architectural integrity.

Required Skills

• 5+ years of expert-level OOP development in Python, Scala, or Java.
• Hands-on experience with MLOps, fine-tuning techniques, and inference frameworks.
• Proficiency in deploying models using vLLM or Triton Inference Server in production containers.
• Strong knowledge of Generative AI RAG lifecycle management and ecosystem.
• Experience with MongoDB, Redis, and containerization technologies.
• Development skills in Angular/React frameworks and building API-based applications (FastAPI, JWT).
• DevOps proficiency with GIT/Bitbucket, Jenkins, SonarQube, pytest, Artifactory, and Ansible.
• Ability to work in large multi-repo codebases using VS Code and collaborative agile teams.

Preferred Skills

• Experience building AI Gateway, policy stores, and observability for RAG/MCP use cases.
• Track record of maintaining large-scale Python/Unix-based systems with performance tuning.

Key Skills

Education

Any Graduate