AI Platform Engineer - 24 months Contract

BGC GROUP PTE. LTD.; Singapore; On-site; SGD 120,000 - 160,000; Full time

Job summary

BGC GROUP PTE. LTD. is seeking an AI Platform Engineer to design, deploy, and operate enterprise-grade AI platforms.

This hands-on role focuses on making AI work in production, not building models, with emphasis on on-premises deployment, Kubernetes, and scalable AI services. You will manage LLM hosting, GPU infrastructure, and inference pipelines, while ensuring security, compliance, and observability across regulated environments.

Qualifications

• 2+ years hands-on experience deploying and managing AI/LLM platforms in production.
• Strong Kubernetes skills; you have run AI workloads on K8s, not just deployed a single container.
• Experience with GPU infrastructure—managing GPU nodes, scheduling, monitoring.
• LLM deployment experience—inference serving, model hosting, prompt pipelines.
• Software engineering fundamentals—clean APIs, CI/CD, containerisation.
• Experience with vector databases and RAG architectures.

Responsibilities

• Deploy and manage AI/LLM platforms in production environments.
• Operate AI agent orchestration platforms in regulated on-premises settings.
• Manage GPU infrastructure and optimize model performance (quantization, vLLM, batching).
• Build reusable APIs, SDKs, and shared AI services for other teams.
• Ensure security, compliance, and observability of AI systems.

Skills

Hands-on production deployment

Kubernetes operations

GPU infrastructure management

LLM deployment & prompt pipelines

Software engineering fundamentals

Vector databases & RAG

Education

Background in Computer Science or Computer Engineering

Tools

Kubernetes

LangChain

LlamaIndex

Job description

About the Role

We're looking for an AI Platform Engineer to design, deploy, and operate enterprise-grade AI platforms — not to build models, but to make AI work in production.

You'll be responsible for:

• Deploying and managing LLM hosting, inference services, and embedding services
• Running AI agent orchestration platforms in a regulated on-premises environment
• Managing GPU infrastructure and optimizing model performance (quantization, vLLM, batching)
• Building reusable APIs, SDKs, and shared AI services that other teams can plug into
• Keeping AI systems secure, compliant, and observable

This is a hands-on engineering role. You'll be in the terminal, on Kubernetes, tuning inference pipelines, and shipping production services — not writing research papers or building dashboards.

Who We're Looking For

You must have:

• 2+ years of hands‑on experience deploying and managing AI/LLM platforms in production
• Strong Kubernetes skills — you've run AI workloads on K8s, not just deployed a single container
• Experience with GPU infrastructure — managing GPU nodes, scheduling, monitoring
• LLM deployment experience — inference serving, model hosting, prompt pipelines
• Software engineering fundamentals — you write clean APIs, use CI/CD, and containerise your work
• Experience with vector databases and RAG architectures

Nice to have:

• Experience with agentic AI frameworks (LangChain, LlamaIndex, multi‑agent systems)
• Model optimisation techniques (quantization, vLLM, batching)
• Experience working in regulated or on‑premise environments (gov, defence, finance)
• Background in Computer Science, Computer Engineering, or related fields