- Hong Kong Hong Kong
Gravitas Recruitment Group Hiring! Work from Home Senior Platform Engineer (AI Infra) - DevOps in Hong Kong - Ricebowl
Senior Platform Engineer (AI Infra) - DevOps
Gravitas Recruitment Group
Share
Save
Working Location
Job Description
Responsibilities
Senior Platform Engineer (AI Infrastructure)
Location: Hong Kong / Remote
About the Role
We are building a highly secure, private AI ecosystem from the ground up. As a Senior AI Platform Engineer, you will design the foundation that allows our team to leverage AI safely and cost-effectively.
This role bridges the gap between classic cloud engineering and cutting-edge AI deployments. You will build a centralized secure gateway for all internal AI traffic and assist our infrastructure team in deploying and tuning open-source models on our own physical data center hardware (GPUs).
Core Requirements (Must-Haves)
What You’ll Do
Bonus Points If You Have (Nice-to-Haves):
Location: Hong Kong / Remote
About the Role
We are building a highly secure, private AI ecosystem from the ground up. As a Senior AI Platform Engineer, you will design the foundation that allows our team to leverage AI safely and cost-effectively.
This role bridges the gap between classic cloud engineering and cutting-edge AI deployments. You will build a centralized secure gateway for all internal AI traffic and assist our infrastructure team in deploying and tuning open-source models on our own physical data center hardware (GPUs).
Core Requirements (Must-Haves)
- Production Container Orchestration: Deep, hands-on production experience with Kubernetes, Docker, and Linux environments. (Must have run this at scale, not just be "familiar" with it).
- Hardware or Local AI Exposure: Practical experience either running local LLM frameworks (like vLLM, TGI, or Triton) OR a rock-solid understanding of managing physical, on-premise servers and bare-metal data centers.
- Security & Access Mindset: A proven track record of caring about cost management, network security, access controls, and API throttling.
- 5+ Years in Infrastructure: Solid background as a Platform, DevOps, or Site Reliability Engineer managing live, production-grade environments.
- Programming & Pipelines: Strong scripting skills in Python alongside experience building automated deployment workflows (CI/CD via GitHub Actions, GitLab, etc.).
What You’ll Do
- Deploy Private AI: Work with our bare-metal infrastructure team to configure, optimize, and run large language models locally on our owned GPU hardware.
- Secure the Gateway: Build, scale, and maintain the central internal API gateway that handles, monitors, and audits all company AI traffic.
- Integrate Identity: Seamlessly connect our AI tools with corporate single sign-on (SSO) systems to automate access management.
- Manage Costs: Track usage metrics and implement strict guardrails to keep infrastructure spend optimized and highly efficient.
- Empower Teams: Create documentation and provide light internal guidance to help non-technical staff use these new tools productively.
Bonus Points If You Have (Nice-to-Haves):
- Background working in highly regulated fields like Fintech, Banking, or Healthcare.
- Experience deploying enterprise identity solutions (Okta, Azure AD / Entra ID, Keycloak)
Important Information
Never provide your bank or credit card details when applying for jobs. Do not transfer any money or complete unrelated online surveys. If you see something suspicious, Report this Job ad.
Learn More