Senior LLMOps Engineer: Production AI Reliability Lead

NCS Pte Ltd; Singapore; On-site; SGD 120,000 - 180,000; Full time

Benefits offered by this job

Health insurance

Learning & development

Job summary

NCS Pte Ltd in Singapore seeks an experienced LLMOps Engineer to deploy, monitor and scale AI-powered services. You will own deployment pipelines, implement CI/CD for containerised AI workloads on Kubernetes, and manage observability, SLAs, and cost efficiency across engagements.

The role spans POC/POV work to steady-state production support with strong collaboration across AI and cloud teams. Two levels are offered (LLMOps and Senior LLMOps) with scope varying by ownership and years of

Qualifications

• 2+ years in DevOps/MLOps/platform engineering with hands-on exposure to production ML systems.
• Hands-on with containers, Kubernetes, CI/CD and Infrastructure-as-Code (Terraform).
• Experience deploying and operating LLM/agentic systems at scale (RAG/flow patterns).
• Strong scripting in Python and/or Go; multi-cloud familiarity (AWS/Azure/GCP).
• Observability tooling (OpenTelemetry, Prometheus, Grafana, ELK/OpenSearch) for AI signals.

Responsibilities

• Own deployment pipeline for LLM/agentic apps with versioned models/prompts and safe rollout.
• Build repeatable CI/CD pipelines (containerised, Kubernetes) ensuring production-grade deployments.
• Monitor latency, errors, drift, hallucination; define SLAs/SLOs with AI Architects.
• Cost & performance: monitor token spend; tune routing between model tiers for cost efficiency.
• During FDE: stand up reusable deployment scaffolding; for production: maintain operations and incident response.

Tools

Docker

Terraform

Kubernetes

Job description

NCS Pte Ltd in Singapore seeks an experienced LLMOps Engineer to deploy, monitor and scale AI-powered services. You will own deployment pipelines, implement CI/CD for containerised AI workloads on Kubernetes, and manage observability, SLAs, and cost efficiency across engagements.

The role spans POC/POV work to steady-state production support with strong collaboration across AI and cloud teams. Two levels are offered (LLMOps and Senior LLMOps) with scope varying by ownership and years of