Machine Learning Platform Engineer (Remote)

Location: Malaysia
Work Arrangement: Fully Remote
Employment Type: Full-time

🚀 Build the Infrastructure Powering the Next Generation of AI

Are you passionate about AI infrastructure, distributed systems, GPU computing and high-performance ML systems?

Join us as an ML Platform Engineer and build the infrastructure that powers our AI capabilities — from model training and evaluation to deployment, inference and production observability.

This is an opportunity to work at the intersection of software engineering, machine learning and infrastructure, solving challenging problems around scale, performance, reliability and cost.

You'll work closely with AI engineers, researchers and product engineers to turn rapidly evolving AI models into reliable, scalable and production-ready systems.

What You'll Do

• Build and operate the ML infrastructure and platforms powering A1's AI products.
• Design systems supporting model training, evaluation, deployment, inference and experimentation.
• Build and optimise model-serving and inference infrastructure for high-throughput and low-latency AI workloads.
• Develop scalable pipelines covering data preparation, training, evaluation, model release and continuous improvement.
• Build platforms and developer tooling that enable AI engineers and researchers to experiment, evaluate and ship models faster.
• Develop evaluation and benchmarking infrastructure to measure model quality, performance and regressions.
• Build production-grade monitoring, observability, tracing and alerting for AI/ML workloads.
• Optimise AI systems across latency, throughput, reliability, scalability and cost efficiency.
• Identify bottlenecks across the ML stack and continuously improve infrastructure and system performance.
• Work closely with AI engineers, researchers and product teams to translate evolving model requirements into production-ready infrastructure.
• Contribute to the architecture and evolution of A1's AI/ML platform and infrastructure stack.

What We're Looking For

• Strong software engineering experience, particularly with Python.
• Hands-on experience building or operating ML/AI infrastructure in production.
• Experience with PyTorch, JAX or similar ML frameworks.
• Experience with model-serving and inference technologies such as vLLM, SGLang, TensorRT-LLM or equivalent.
• Strong understanding of distributed systems and cloud infrastructure.
• Experience building ML/data pipelines and workflow orchestration.
• Understanding of GPU infrastructure, GPU workloads and performance optimisation.
• Experience with monitoring, observability, tracing and production infrastructure.
• Experience with vector databases and retrieval infrastructure is an advantage.
• Strong understanding of system performance, scalability, reliability and cost optimisation.
• Ability to work effectively with AI engineers, researchers and product engineers.

⭐ Why Join US?

Build the Engine Behind AI

You won't simply consume AI models — you'll build the infrastructure that allows AI systems to operate reliably at scale.

Work With Cutting-Edge Technology

Get hands-on experience with GPU infrastructure, LLM serving, distributed systems, PyTorch/JAX, vLLM, SGLang and TensorRT-LLM.

Solve Real Engineering Challenges

Work on challenging problems involving high-throughput inference, low latency, scalability, reliability and infrastructure cost optimisation.

Work Alongside AI Experts

Collaborate closely with AI engineers, researchers and product engineers, gaining exposure across the full AI technology stack.