Senior Devops Engineer

luxoft information technology (singapore) pte. ltd.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Luxoft Information Technology (Singapore) Pte. Ltd. partners with a leading Singapore financial institution to drive enterprise-wide AI transformation, deploying and operating LLMs, AI agents, and intelligent automation in a highly regulated banking environment.

The AI DevOps Engineer / MLOps Engineer will build secure, scalable deployment pipelines, integrate with enterprise applications via REST APIs, and ensure production readiness across development, UAT and production environments.

Qualifications

• 6-10 years in DevOps, Platform or Cloud Eng.
• Hands-on Jenkins expertise.
• Experience with GitHub/GitHub Actions/GitLab/Bitbucket.
• Deploying AI/ML models from Hugging Face.
• Docker and Kubernetes/OpenShift proficient.
• Linux system administration experience.
• Bash/Python scripting experience.
• CI/CD pipeline automation experience.
• IaC with Terraform or Ansible.
• Experience with cloud platforms (AWS/Azure/GCP).
• GPU-enabled environments and NVIDIA CUDA knowledge.
• Experience with model serving platforms like vLLM, Ollama, Triton, TGI.
• REST APIs and microservices knowledge.
• Monitoring/logging tools: Prometheus, Grafana, ELK, Splunk, Dynatrace.

Responsibilities

• Design, build, and maintain CI/CD pipelines for AI/ML deployment.
• Deploy LLMs from Hugging Face into dev, UAT, and production.
• Automate model packaging, testing, and release.
• Manage Kubernetes/OpenShift AI platforms for hosting and inference.
• Build deployment pipelines using Jenkins, GitHub Actions, GitLab CI.
• Containerise AI apps with Docker and deploy to clusters.
• Integrate AI solutions with enterprise apps via REST APIs.
• Manage model lifecycle, rollback, monitoring, and production support.
• Implement IaC (Terraform/Ansible) for AI platform provisioning.
• Configure model serving platforms like vLLM, Ollama, Triton, TGI.
• Monitor health with Prometheus, Grafana, ELK, Dynatrace, Splunk.
• Optimise GPU resources and troubleshoot performance.
• Collaborate with AI engineers to productionise models.
• Ensure security, governance, compliance in banking environment.
• Participate in production releases and incident management.

Skills

Jenkins

GitHub Actions

GitLab

Docker

Kubernetes

Terraform

Ansible

Python

Linux

CI/CD

REST APIs

GPU/CUDA

Tools

Artifactory

Nexus

Docker Registry

Hugging Face

Triton

Ollama

vLLM

NVIDIA CUDA

Job description

Project Description:Our client is a leading Singapore-based financial institution embarking on an enterprise-wide AI transformation programme to accelerate the adoption of Generative AI across business and technology functions. The programme focuses on deploying and operating Large Language Models (LLMs), AI agents, and intelligent automation solutions within a secure, highly regulated banking environment.
As part of this strategic initiative, we are looking for an experienced AI DevOps Engineer / MLOps Engineer to build, automate, and manage AI model deployment pipelines, enabling secure, scalable, and reliable delivery of AI solutions across the bank.
You will work closely with AI Engineers, Data Scientists, Platform Engineers, Security teams, and Application Development teams to operationalise AI workloads on modern cloud and container platforms.

Responsibilities:

• Design, build, and maintain CI/CD pipelines for AI/ML model deployment.
• Deploy Large Language Models (LLMs) from Hugging Face and other model repositories into development, UAT, and production environments.
• Automate model packaging, versioning, testing, and release using DevOps best practices.
• Manage Kubernetes/OpenShift based AI platforms for model hosting and inference.
• Build deployment pipelines using Jenkins, GitHub Actions, GitLab CI, or similar CI/CD tools.
• Containerise AI applications using Docker and deploy them into Kubernetes clusters.
• Integrate AI solutions with enterprise applications using REST APIs and microservices.
• Manage model lifecycle, rollback strategies, monitoring, and production support.
• Implement Infrastructure as Code (Terraform/Ansible) for AI platform provisioning.
• Configure model serving platforms such as vLLM, Ollama, Triton Inference Server, or similar.
• Monitor application and model health using Prometheus, Grafana, ELK, Dynatrace, or Splunk.
• Optimise GPU resource utilisation and troubleshoot model performance issues.
• Collaborate with AI Engineers to productionise new models and inference pipelines.
• Ensure security, governance, and compliance requirements are met within the banking environment.
• Participate in production releases, incident management, and continuous platform improvements.

Mandatory Skills Description:

• 6-10 years of experience in DevOps, Platform Engineering, or Cloud Engineering.
• Strong hands-on experience with Jenkins.
• Strong knowledge of GitHub, GitHub Actions, GitLab, or Bitbucket.
• Experience deploying AI/ML models from Hugging Face or similar model repositories.
• Strong Docker and Kubernetes/OpenShift experience.
• Experience with Linux system administration.
• Hands-on scripting experience using Bash, Python, or Shell scripting.
• Experience with CI/CD pipeline automation.
• Experience with Infrastructure as Code using Terraform or Ansible.
• Knowledge of container registries such as Artifactory, Nexus, or Docker Registry.
• Experience working with cloud platforms such as AWS, Azure, or GCP.
• Understanding of GPU-enabled environments and NVIDIA CUDA ecosystem.
• Experience configuring model serving platforms such as:
• vLLM
• Ollama
• NVIDIA Triton Inference Server
• Text Generation Inference (TGI)
• Knowledge of REST APIs and microservices architecture.
• Experience with monitoring and logging tools including Prometheus, Grafana, ELK, Splunk, or Dynatrace.
• Strong troubleshooting and production support skills.
• Excellent communication and stakeholder management skills.

Nice-to-Have Skills Description:

• Experience with LangChain, LangGraph, or AI Agent frameworks.
• Experience with Vector Databases (Pinecone, Milvus, Weaviate, OpenSearch, pgvector).
• Knowledge of Retrieval-Augmented Generation (RAG) architecture.
• Experience deploying Llama, Mistral, DeepSeek, Qwen, or other open-source LLMs.
• Experience with MLflow, Kubeflow, or other MLOps platforms.
• Familiarity with Kafka or RabbitMQ.
• Experience with API Gateway and service mesh technologies.
• Knowledge of security scanning tools such as Trivy, SonarQube, Checkmarx, or Snyk.
• Experience implementing DevSecOps practices.
• Agile/Scrum delivery experience.
• Previous experience within Banking, Capital Markets, or Financial Services.
• Experience supporting AI platforms in production environments.