LLMOps Engineer: Production AI Deployment & Reliability

NCS Group; Singapore; On-site; SGD 70,000 - 110,000; Full time

Benefits offered by this job

Career development opportunities

Collaborative culture

Continuous learning programs

Job summary

NCS Group is seeking a DevOps Engineer to join NCS AI Central's Forward Deployed Engineering team. You will own deployment pipelines for LLM/agentic apps, build repeatable CI/CD on Kubernetes, and harden production-grade deployments for POC/POV to scale.

You will instrument observability, track SLAs, and optimize token costs while collaborating with AI Engineers and Cloud Architects. The role blends rapid POC work with disciplined production operations, mentoring on LLMOps and contributing to

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 scripting/programming ability (Python and/or Go), comfortable working across cloud platforms (AWS/Azure/GCP); exposure to GCC/HCC a plus.
• Working knowledge of observability tooling (OpenTelemetry, Prometheus/Grafana, ELK/OpenSearch) applied to AI-specific signals.
• Comfortable operating in fast-paced POC/POV settings and disciplined SLA-driven production support environments.
• Working knowledge of the China AI model/tech stack (DeepSeek, Qwen, GLM, Kimi, MiniMax) — deployment patterns, licensing, and self-hosting requirements.

Responsibilities

• 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) to ship models and prompts without manual intervention.
• Support rapid environment spin-up for POC/POV work, then harden pipelines into production-grade deployments for scaling engagements.
• Instrument LLM applications with observability for latency, error rates, drift, and hallucination signals; define SLAs/SLOs with AI Architects.
• Set up alerting and runbooks for production AI systems to catch issues before clients notice.
• Monitor token spend and inference cost; tune routing between model tiers for cost-performance at scale.
• Stand up reusable deployment scaffolding during FDE engagements and own steady-state production operations; contribute to internal asset library.
• Mentor engineers on LLMOps practices; participate in Production Readiness Review gate reviews.

Skills

LLMOps

Kubernetes

CI/CD

Terraform

Python/Go

Cloud platforms

Observability

Model gateways

Vector databases

China AI stack

Tools

GitHub Actions

GitLab

Jenkins

OpenTelemetry

Prometheus

Grafana

ELK/OpenSearch

Terraform

vLLM/TGI

Job description

NCS Group is seeking a DevOps Engineer to join NCS AI Central's Forward Deployed Engineering team. You will own deployment pipelines for LLM/agentic apps, build repeatable CI/CD on Kubernetes, and harden production-grade deployments for POC/POV to scale.

You will instrument observability, track SLAs, and optimize token costs while collaborating with AI Engineers and Cloud Architects. The role blends rapid POC work with disciplined production operations, mentoring on LLMOps and contributing to