Site Reliability Engineer - AIOps, LLMOps, MLOps

About the role

Avensys Consulting is seeking a mid‑level Site Reliability Engineer to own the reliability of AI, LLM and ML operations. You will design, automate and monitor end‑to‑end pipelines that train, deploy and evaluate models, ensuring high availability and performance across our AI platform.

Key responsibilities

• Implement automated pipelines and observability for AI model training, deployment and evaluation.
• Drive AIOps‑based reliability, including model retraining triggers and guardrail enforcement.
• Design and operate the AI reliability stack for training, inference and evaluation workloads.
• Integrate telemetry and monitoring to track model health, drift, latency and GPU utilization.
• Automate incident detection, correlation and remediation using AI‑driven alerting.
• Collaborate with AI Safety and Security teams to enforce version control, guardrails and change governance.
• Establish monitoring baselines, SLOs and AIOps diagnostics to reduce MTTD and MTTR.
• Maintain operational documentation and audit readiness for AI components.

Required profile

• Hands‑on experience with AI/ML pipeline orchestration and model lifecycle automation.
• Deep understanding of MLOps, LLMOps and AIOps frameworks for CI/CD at scale.
• Knowledge of data governance, evaluation frameworks and DevSecOps principles for AI pipelines.
• Ability to work collaboratively with cross‑functional safety and security teams.
• Mid‑level management experience in a technology services environment.

Required skills

• Kubeflow
• MLflow
• Airflow
• Azure ML
• CI/CD pipelines for AI/ML
• Observability and telemetry integration
• GPU utilization monitoring
• Promptfoo
• Portkey
• RAG validation
• DevSecOps for AI pipelines

What we offer

• Contract role (6‑month renewable)
• Competitive monthly salary SGD 6,000‑8,000
• On‑site work at our Singapore office
• Opportunity to work on cutting‑edge AI reliability projects
• Supportive environment with focus on work‑life balance