AI/ML Platform Reliability Engineer (L2)

Tata Consultancy Services Limited; Indonesia; On-site; IDR 300,000,000 - 600,000,000; Full time

Job summary

Tata Consultancy Services Limited is seeking an experienced AI Platform Support Engineer to monitor AI/ML models, manage inference endpoints, and ensure robust performance in a production environment.

The role emphasizes incident resolution, data validation, and release management, with on-call rotations and continuous service improvements across global teams. Strong Python skills and familiarity with MLOps and RAG architectures are essential.

Qualifications

• 5–7 years in application/platform support or SRE.
• Bachelor's Degree in CS/IT/Engineering/Data Science or related field.
• Experience with enterprise-scale production environments with strict SLA requirements.
• Ability to work independently and collaborate across global teams.

Responsibilities

• Monitor and support AI/ML models, inference endpoints, and RAG pipelines in production environments.
• Investigate and resolve model, application, and platform incidents, including inference failures, latency issues, and service degradation.
• Analyze logs, metrics, traces, and quality signals to identify root causes and restore services.
• Validate data sources, retrieval systems, embeddings, and other dependencies impacting AI application performance.
• Support controlled deployments, release management, rollback activities, and post-release validation.
• Coordinate major incidents and collaborate with engineering teams for issue resolution.
• Escalate platform, infrastructure, or model defects to relevant development and engineering teams.
• Ensure compliance with SLA, security, change management, and operational standards.
• Maintain system documentation, incident reports, and knowledge articles.
• Participate in on-call support rotations and contribute to continuous service improvement initiatives.

Skills

Python

AI/ML platforms

MLOps

LLM Operations

Prompt Engineering

RAG architectures

APIs & distributed systems

Cloud monitoring

ITIL/Incident Mgmt

24x7 operations

Analytical skills

Education

Bachelor's Degree

Tools

Azure

AWS

Google Cloud Platform

Kubernetes

Docker

Grafana

Prometheus

Datadog

CloudWatch

Azure Monitor

Job description

Tata Consultancy Services Limited is seeking an experienced AI Platform Support Engineer to monitor AI/ML models, manage inference endpoints, and ensure robust performance in a production environment.

The role emphasizes incident resolution, data validation, and release management, with on-call rotations and continuous service improvements across global teams. Strong Python skills and familiarity with MLOps and RAG architectures are essential.