Senior LLMOps Engineer: Production AI Pipelines

Ncs; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

NCS invites experienced LLMOps Engineers to join NCS AI Central in Singapore, delivering production-grade AI deployments across fast-paced POC/POV to steady-state operations. You will own deployment pipelines, observability, and cost optimization for LLM services, collaborating with AI architects and cloud teams to scale reliable AI systems.

The role spans from POC/POV deployments to production maintenance, with emphasis on reusable patterns, SLA-driven operations, and mentorship of junior

Qualifications

• 2+ years in DevOps/MLOps/platform engineering, with hands-on exposure to LLM or ML systems in production; 5+ years with end-to-end ownership expected at Senior level.
• Hands-on with containers, Kubernetes, CI/CD (GitHub Actions/GitLab/Jenkins), and Infrastructure-as-Code (Terraform).
• Practical experience deploying and operating LLM applications (RAG/agentic systems) at scale, including model gateway/routing patterns.
• Strong programming ability (Python and/or Go), comfortable across AWS/Azure/GCP; GCC/HCC exposure a plus.
• Working knowledge of observability tooling (OpenTelemetry, Prometheus/Grafana, ELK/OpenSearch) applied to AI signals.
• Comfortable in fast-paced POC/POV settings and disciplined, SLA-driven production support.
• Working knowledge of China AI stack (DeepSeek, Qwen, GLM, Kimi, MiniMax) deployment patterns, licensing, self-hosting.

Responsibilities

• Model & Deployment Operations
• Own the deployment pipeline for LLM and agentic applications - versioning models, prompts, and configurations as code, with safe rollout and rollback paths.
• Build repeatable CI/CD pipelines for AI services (containerised, on Kubernetes) so new model or prompt versions ship without manual intervention.
• Support rapid, disposable environment spin-up for FDE POC/POV work, then harden the same pipeline into a production-grade deployment when an engagement scales.
• Monitoring & Reliability
• Instrument LLM applications with observability for latency, error rates, output drift, and hallucination signals - not just infrastructure uptime.
• Define and track SLAs/SLOs for production AI services in partnership with AI Architects and Solution Architects.
• Set up alerting and runbooks so issues in live AI systems are caught and triaged before clients notice.
• Cost & Performance Management
• Monitor token spend and inference cost per model/engagement; flag anomalies and right-sizing opportunities with AI FinOps.
• Tune routing between model tiers for cost-performance balance at production scale.
• FDE & Development/Maintenance Coverage
• During FDE engagements: stand up lightweight, reusable deployment scaffolding for rapid iteration without operational overhead.
• During system development & maintenance: own steady-state production operations, patching, upgrades, and incident response.
• Contribute reusable deployment patterns back into the internal asset library.
• Collaboration
• Work closely with AI Engineers, Cloud Architects, and AI Site-facing leads for smooth handoff from POC to Scale to Operate.
• Mentor engineers on LLMOps and participate in PRR gate reviews.

Skills

DevOps/MLOps experience

LLM/ML production

End-to-end ownership

Containers

Kubernetes

CI/CD

Terraform

Model routing

Python

Go

Cloud platforms

OpenTelemetry

Prometheus

Grafana

ELK/OpenSearch

Postgres

Redis

pgvector

Pinecone

Weaviate

GitHub Actions

GitLab

Jenkins

vLLM/TGI

Python

Go

Docker

Helm

Argo CD

Terraform

Vault

Tools

Docker

Kubernetes

Helm

Argo CD

Terraform

Vault

OpenTelemetry

Prometheus

Grafana

ELK/OpenSearch

Postgres

Redis

pgvector

Pinecone

Weaviate

GitHub Actions

GitLab

Jenkins

vLLM/TGI

Python

Go

Job description

NCS invites experienced LLMOps Engineers to join NCS AI Central in Singapore, delivering production-grade AI deployments across fast-paced POC/POV to steady-state operations. You will own deployment pipelines, observability, and cost optimization for LLM services, collaborating with AI architects and cloud teams to scale reliable AI systems.

The role spans from POC/POV deployments to production maintenance, with emphasis on reusable patterns, SLA-driven operations, and mentorship of junior