Senior Site Reliability Engineer

YTL AI Labs; Kuala Lumpur; On-site; MYR 180,000 - 300,000; Full time

Job summary

YTL AI Labs is seeking a Senior Site Reliability Engineer to ensure the reliability, scalability, and operational integrity of our sovereign AI platform. You will own critical services, drive observability, and contribute to GPU-inference infrastructure while maintaining data residency and security standards.

Working within Platform & Infrastructure, you’ll mentor engineers, participate in on-call incidents, and advance CI/CD, IaC, and deployment patterns to keep production healthy at scale in

Qualifications

• Five or more years in software or infrastructure engineering on production systems.
• Proven track record of improving reliability and operability of distributed systems, with SLOs, observability, and incident response.
• Solid working knowledge of cloud infrastructure, Kubernetes, networking, identity, and security fundamentals, with hands-on exposure to GPU-backed or compute-intensive workloads.
• Proficiency in at least one systems or scripting language (Python, Go, or equivalent) and experience building internal tooling and automation.
• Experience with modern AI platform operations, including inference infrastructure and reliability/cost challenges for LLM workloads.
• Habit of driving reliability issues to root cause and delivering lasting fixes rather than workarounds.
• Ability to communicate operational risk and system health clearly to engineering and non-engineering audiences.

Responsibilities

• Own SLOs, error budgets, and alerting for one or more critical services.
• Build observability across metrics, logging, distributed tracing, and synthetic monitoring.
• Join the on-call rotation, help run incidents, and drive blameless post-incident actions to closure.
• Build automation that cuts time to detection and recovery.
• Improve infrastructure-as-code, CI/CD, and deployment patterns, with proper testing and rollback.
• Support multi-tenant, sovereign-capable deployments with data residency and network isolation requirements.
• Contribute to capacity planning and cost optimisation for GPU inference infrastructure.
• Keep owned services secure: identity, secrets, patching, and container and Kubernetes hardening.
• Embed reliability into designs early and mentor junior and mid-level engineers.

Skills

SRE/infra experience

Observability & incident response

Kubernetes

Cloud infrastructure

Python/Go scripting

AI platform operations

Root cause analysis

Communication

Tools

CI/CD tooling

GPU inference infrastructure

Job description

At YTL AI Labs, we build sovereign AI models that perform on par with the world’s best—while staying grounded in local needs, values, and context. Our flagship model, Ilmu, is designed to be culturally aware, contextually intelligent, and fluent in Bahasa Melayu, delivering cutting-edge solutions that empower Malaysian businesses with intelligence that truly understands the market and the people they serve.

As pioneers of sovereign AI, we believe every nation should have the power to shape its own intelligence—guided by its people, priorities, and principles.

Role Summary

The Senior Site Reliability Engineer helps ensure the reliability, scalability, and operational integrity of the YTL AI Labs platform. Working within the Platform & Infrastructure function, the role builds and operates the systems, tooling, and practices that allow product and solutions teams to run AI workloads with confidence.

This is a hands‑on engineering role. The Senior SRE owns the reliability of assigned services, takes part in incident response, and delivers the improvements that keep production healthy. The role works to the platform‑wide reliability standards set by the Principal SRE and takes day‑to‑day direction from the Lead SRE for the services in scope. It operates at the boundary between infrastructure, software engineering, and product delivery, and works closely with engineers across the organisation.

What you’ll do

• Own SLOs, error budgets, and alerting for one or more critical services
• Build out observability across metrics, logging, distributed tracing, and synthetic monitoring
• Join the on‑call rotation, help run incidents, and drive blameless post‑incident actions to closure
• Build automation that cuts time to detection and recovery
• Improve infrastructure‑as‑code, CI/CD, and deployment patterns, with proper testing and rollback
• Support multi‑tenant, sovereign‑capable deployments with data residency and network isolation requirements
• Contribute to capacity planning and cost optimisation for GPU inference infrastructure
• Keep owned services secure: identity, secrets, patching, and container and Kubernetes hardening
• Embed reliability into designs early and mentor junior and mid‑level engineers

What we’re looking for

• Five or more years in software engineering, infrastructure engineering, or site reliability, including operating production systems at meaningful scale
• A track record of improving the reliability and operability of distributed systems, including working with SLOs, observability, and incident response
• Solid working knowledge of cloud infrastructure, Kubernetes, networking, identity, and security fundamentals, with hands‑on exposure to GPU‑backed or compute‑intensive workloads
• Proficiency in at least one systems or scripting language (Python, Go, or equivalent) and experience building internal tooling and automation
• Working understanding of modern AI platform operations, including inference infrastructure and the reliability and cost challenges specific to LLM workloads
• A habit of driving reliability issues to root cause and delivering lasting fixes rather than repeated workaroundsAb
• Ability to communicate operational risk and system health clearly to both engineering and non‑engineering audiences

Nice to have

• Experience operating sovereign or on‑premises AI infrastructure for government or regulated industry clients in Malaysia or the wider region
• Experience with ML infrastructure tooling, including model registries, inference servers (TensorRT‑LLM, vLLM, or equivalent), and GPU cluster management
• Exposure to multi‑tenant SaaS platform operations, including per‑tenant isolation and quota management