AI/ML Engineer (DevOps | MLOps | LLM | 5000-7000 SGD | GOVT)

BGC GROUP PTE. LTD.; Singapore; On-site; SGD 80,000 - 100,000; Full time

Job summary

A technology specialist firm in Singapore is seeking an experienced AI/ML Engineer to develop and deploy AI products while managing AI infrastructure. Responsibilities include design and implementation of backend services, inference optimization, and ensuring compliance with security standards. Ideal candidates should have significant experience in DevOps and MLOps, with expertise in deploying LLMs and a solid understanding of security practices. The role offers a salary of 5000-7000 SGD plus bonuses.

Qualifications

• 5+ years in DevOps, MLOps, with 2+ years in AI/ML systems.
• Hands-on experience deploying and optimizing LLMs in production.
• Strong understanding of AI/MLOps practices and tools.

Responsibilities

• Design and develop backend API services for AI functionalities.
• Deploy and manage large-scale LLMs in containerized environments.
• Tune inference performance using model optimization techniques.
• Design and manage scalable GPU infrastructure for AI workloads.

Skills

DevOps practices

MLOps tools

Container technologies

Scripting skills

Inference optimization techniques

GPU infrastructure

Secure software development practices

Education

Bachelor’s or Master’s degree in Computer Science or related field

Tools

Redhat OCP

MLflow

Kubeflow

TensorRT

ONNX Runtime

DeepSpeed

Python

Bash

Job description

• Job Title: AI/ML Engineer (DevOps | MLOps | 5000-7000 SGD | GOVT)
• Duration: 24 months
• Location: Bukit Merah Central / Depot Rd
• Salary: 5000-7000 + AWS + Performance Bonus
• Eligibility: Only Singaporeans

Responsibilities

• Development and Deployment of AI products and AI-Driven Backend services:
• Design and develop backend API services for AI-powered functionalities that are reusable and scalable to support business use cases (e.g. OCR, document parsing, embedding model APIs)
• Deploy and manage large-scale LLMs (e.g., LLaMA, Mistral, GPT-based models) in containerized environments using tools like Kubernetes (Redhat OCP preferred) and vLLM and integrate into RESETful or gRPC API endpoints.
• Package, version, document, and deploy AI/ML models/services using MLOps frameworks like MLflow, Kubeflow, or an enterprise AI/ML tool such as Dataiku.

Inference Optimization

• Tune inference performance using model quantization, tensor parallelism, low-level optimization libraries (e.g., TensorRT, ONNX Runtime, DeepSpeed).
• Implement dynamic batching and request multiplexing for low-latency, high-throughput serving.
• Profile and monitor model inference workloads to identify and remove performance bottlenecks.

AI Infrastructure Management

• Design and manage scalable GPU/accelerator infrastructure (on-prem) for AI training and inference workloads.
• Maintain efficient GPU job scheduling with tools like Redhat OCP.

Security and Compliance

• Embed security throughout the AI deployment lifecycle including model validation, image signing, runtime protection, and API security.
• Ensure infrastructure complies with enterprise security standards (e.g., NIST, ISO 27001).
• Collaborate with security and compliance teams to perform threat modeling and secure deployment assessments.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Mathematics, Statistics, or a related field
• 5+ years in DevOps, MLOps, with 2+ years focusing on AI/ML systems.
• Strong understanding of AI/MLOps practices and tools
• Hands‑on experience deploying and optimizing LLMs or transformer‑based models in production.
• Proficiency in container technologies (preferably Redhat OCP)
• Strong scripting and automation skills (Python, Bash, etc.).
• Familiarity with inference optimization techniques (quantization, batching, parallelism).
• Solid understanding of GPU infrastructure and performance tuning.
• Deep knowledge of secure software development practices and DevSecOps tooling