Lead Engineer/ Engineer, MLOps / SRE (Developer Experience), xCloud

HTX (Home Team Science & Technology Agency); Singapore; On-site; SGD 140,000 - 190,000; Full time

Job summary

HTX is Singapore's Science and Technology agency advancing transformative AI solutions for public safety. The MLOps/SRE Engineer will deploy, operate, and optimize a production LLM system in our secure infrastructure, ensuring reliability, performance, and cost-efficiency across the stack from inference to vector databases and observability.

This role requires hands-on experience with LLMs in production, strong Kubernetes, and a security‑minded approach in a regulated environment.

Qualifications

• 4+ years in MLOps/SRE/DevOps with 1+ year in ML/AI systems.
• Hands-on production deployment/operation of LLMs (vLLM, TensorRT-LLM, or similar).
• Strong Kubernetes expertise including operators, StatefulSets, and GPU scheduling.
• Experience with observability tools (Prometheus, Grafana, ELK/Elastic Stack).
• Solid Python and Bash scripting for automation.
• Knowledge of vector databases (Milvus, Weaviate, Qdrant, Pinecone).
• Experience with infrastructure-as-code (Terraform, Helm, Kustomize).
• Experience with NVIDIA GPUs (A100/H100) and DCGM monitoring.
• Familiarity with Ray clusters, Kubeflow, or MLflow.
• Security-conscious in secure or regulated environments.

Responsibilities

• LLM Deployment: Deploy and manage LLM models using vLLM/TensorRT-LLM on GPU infrastructure.
• Infrastructure Management: Provision and maintain vector databases, orchestration services, Redis/queue systems, and API gateways.
• Performance Optimization: Profile and tune LLM inference, batching, context caching, and quantization.
• Observability: Implement monitoring with Prometheus, Grafana, DCGM exporters, and Elastic Stack.
• Reliability Engineering: Establish SLOs/SLIs, auto-scaling, failure recovery, and chaos engineering.
• Cost Optimization: Monitor GPU utilization and inference costs, reduce token usage where possible.
• Security & Compliance: Ensure secure network boundaries, manage secrets, maintain audit logs.
• Incident Response: Participate in on-call, troubleshoot incidents, conduct root cause analysis.
• Capacity Planning: Model load, forecast GPU requirements, scale platform with adoption.

Skills

MLOps

SRE

DevOps

LLM Deployment

Kubernetes

Python

Bash scripting

Vector databases

Terraform

NVIDIA GPUs

Tools

Milvus

Weaviate

Qdrant

Pinecone

Redis

Elastic Stack

Prometheus

Grafana

DCGM

Job description

What The Role Is

HTX is Singapore's Science and Technology agency that brings together diverse scientific and engineering capabilities to develop transformative, operationally ready solutions for public safety. As a statutory board under the Ministry of Home Affairs, HTX works at the forefront of science and technology to empower the Home Team with cutting‑edge capabilities. Guided by our mission to amplify, augment and accelerate the Home Team's advantage, we are committed to keeping Singapore the safest place on planet Earth.

xCloud is dedicated to elevating the enterprise experience through cutting‑edge cloud capabilities, including:

• Sustainable enterprise data centres
• Hybrid cloud platforms
• Advanced cloud security measures
• Integrated Development, Security, and Operations (DevSecOps)
• Innovative enterprise Software-as-a-Service (SaaS) solutions
• AI-powered enterprise applications

As the MLOps/SRE Engineer for HTX's developer experience squad, you will be responsible for deploying, operating, and optimizing a production LLM system in our secure infrastructure. You will ensure the agentic code assistant is reliable, performant, and cost‑effective, managing the full stack from LLM inference to vector databases, orchestration services, and observability. This role combines deep MLOps expertise with SRE discipline to support Home Team's critical AI infrastructure.

What You Will Be Working On

• LLM Deployment: Deploy and manage LLM models using vLLM/TensorRT-LLM on our GPU infrastructure, optimizing for throughput, latency, and GPU utilization
• Infrastructure Management: Provision and maintain the supporting infrastructure including vector databases (for RAG), orchestration services, Redis/queue systems, and API gateways
• Performance Optimization: Profile and tune LLM inference performance, experiment with batching strategies, context caching, and quantization techniques to maximize throughput within GPU constraints
• Observability: Implement comprehensive monitoring using Prometheus, Grafana, DCGM exporters, and Elastic Stack to track inference latency, token throughput, cache hit rates, and system health
• Reliability Engineering: Establish SLOs/SLIs, implement auto‑scaling policies, design failure recovery mechanisms, and conduct chaos engineering to ensure high uptime
• Cost Optimization: Monitor GPU utilization and inference costs, identify optimization opportunities, and implement strategies to reduce token usage and compute spend
• Security & Compliance: Ensure all components operate within secure network boundaries, manage secrets and credentials securely, and maintain audit logs for compliance
• Incident Response: Participate in on‑call rotation, troubleshoot production incidents, conduct root cause analysis, and implement preventive measures
• Capacity Planning: Model future load, forecast GPU requirements, and work with infrastructure teams to scale the platform as adoption grows

What We Are Looking For

• 4+ years of experience in MLOps, SRE, or DevOps roles, with at least 1 year working with ML/AI systems
• Hands‑on experience deploying and operating LLMs in production (vLLM, TGI, TensorRT‑LLM, or similar)
• Strong Kubernetes expertise including operators, StatefulSets, and GPU scheduling
• Deep understanding of GPU architecture, and inference optimization techniques
• Experience with observability tools (Prometheus, Grafana, ELK/Elastic Stack)
• Solid Python and Bash scripting skills for automation
• Knowledge of vector databases (Milvus, Weaviate, Qdrant, or Pinecone)
• Experience with infrastructure-as-code (Terraform, Helm, Kustomize)
• Experience with NVIDIA GPUs (A100/H100/B200) and DCGM monitoring
• Understanding of LLM inference concepts: KV cache, continuous batching, PagedAttention
• Familiarity with Ray clusters, Kubeflow, or MLflow
• Background in SRE practices: SLO/SLI definition, error budgets, incident management
• Experience with secure or regulated environments
• Knowledge of LiteLLM, Kong Gateway, or API management platforms
• Systems thinking with ability to diagnose complex issues across the ML stack
• Data‑driven decision making using metrics and telemetry
• Proactive mindset focused on reliability, automation, and preventive measures
• Strong debugging skills for GPU, networking, and distributed systems issues
• Clear incident communication and documentation
• Collaborative approach working with data scientists, ML engineers, and platform teams