Job Description

Hi,

We openings for SRE Devops ML frmaework, With one of Product based client, for Bangalore (Contract to hire).

Job Functions:

You will be a member of our AI Platform Team, supporting the next generation AI architecture for various research and engineering teams within the organization.

? You'll partner with vendors and the infrastructure engineering team for security and service availability

? You'll fi x production issues with engineering teams, researchers, data scientists, including performance and functional issues

? Diagnose and solve customer technical problems

? Participate in training customers and prepare reports on customer issues

? Be responsible for customer service improvements and recommend product improvements

? Write support documentation

? You'll design and implement zero-downtime to monitor and accomplish a highly available service (99.999%)

? As a support engineer, fi nd opportunities to automate as part of the problem management process, creating automation to avoid issues.

? Defi ne engineering excellence for operational maturity

? You'll work together with AI platform developers to provide the CI/CD model to deploy and confi gure the production system automatically

? Develop and follow operational standard processes for tools and automation development. Including: Style guides, versioning practices, source control, branching and merging patterns and advising other engineers on development standards

? Deliver solutions that accelerate the activities, phenomenal engineers would perform through automation, deep domain expertise, and knowledge sharing

Required Skills:

? Demonstrated ability in designing, building, refactoring and releasing software written in Python.

? Hands-on experience with ML frameworks such as PyTorch, TensorFlow, Triton.

? Ability to handle framework-related issues, version upgrades, and compatibility with data processing / model training environments.

? Experience with AI/ML model training and inferencing platforms is a big plus.

? Experience with the LLM fi ne tuning system is a big plus.

? Debugging and triaging skills.

? Cloud technologies like Kubernetes, Docker and Linux fundamentals.

? Familiar with DevOps practices and continuous testing.

? DevOps pipeline and automations: app deployment/confi guration & performance monitoring.

? Test automations, Jenkins CI/CD.

? Excellent communication, presentation, and leadership skills to be able to work and collaborate with partners, customers and engineering teams.

? Well organized and able to manage multiple projects in a fast paced and demanding environment.

? Good oral/reading/writing English ability.

Note: Max notice period should be less than 30days.

Interested can share their updated resume to sowmya.hp@prospaneinc.com

Job Type: Contractual / Temporary
Contract length: 24 months

Pay: ₹2,500,000.00 - ₹3,500,000.00 per year

Benefits:

Health insurance
Expected Start Date: 31/10/2025