Want to know if this job is worth applying to?
中国
Onsite
About A1
There are over 5 billion users using basic applications today such email, notes, tasks that are not AI-native. Our mission is to build a proactive smart assistant for everyday users to bring intelligence to conversations, errands, organising and workflows, with minimal prompting.
Our product focuses on achieving high reliability for long-running workflows, persistent context, and real-world task completion. The system must handle multi-step reasoning, interact with external tools, and remain reliable despite non-deterministic model behavior. Our objective is to help users complete tasks daily enjoyable with over ~90%* reduced time.
About the Role
As an ML Platform Engineer, you will build the infrastructure and systems that power A1's AI capabilities.
You will design and operate the systems behind the AI stack, from model training and evaluation to deployment, inference, observability, and continuous improvement.
You will work closely with AI engineers, researchers, and product engineers to turn models into reliable, scalable, and cost-efficient production systems. You will build the platforms, tooling, and infrastructure that enable the team to experiment quickly and bring AI capabilities to production with confidence.
Focus
Build and operate the ML infrastructure and platforms powering A1’s AI products
Design systems for model training, evaluation, deployment, inference, and experimentation
Build and optimise model serving and inference infrastructure for high-throughput and low-latency workloads
Improve reliability, scalability, latency, and cost efficiency of AI systems
Develop reliable pipelines for data preparation, training, evaluation, model release, and continuous improvement
Build platforms and 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 observability, monitoring, tracing, and alerting for AI/ML workloads
Improve AI systems across reliability, scalability, latency, throughput, and cost
Identify bottlenecks across the ML stack and continuously improve system performance
Work closely with AI engineers, researchers, and product teams to turn evolving model requirements into production-ready infrastructure
Tech Stack
Python
PyTorch / JAX
LLM and ML serving infrastructure such as vLLM, SGLang, or TensorRT-LLM
Cloud infrastructure
Distributed systems
ML/data pipelines and workflow orchestration
GPU infrastructure and performance tooling
Vector databases and retrieval infrastructure
Ideal Experience
Strong software engineering fundamentals and experience building production systems
Experience building ML infrastructure, platforms, or production machine learning systems
Experience with model deployment, inference, evaluation, or data pipelines
Strong understanding of distributed systems and system reliability
Ability to write clean, maintainable, production-quality code
Comfortable working in ambiguous, fast-moving environments
Bias toward ownership, experimentation, and continuous improvement
Outcomes
AI infrastructure reliably supports production workloads at scale
Models can be trained, evaluated, deployed, and improved efficiently
Inference systems deliver strong latency, throughput, reliability, and cost efficiency
ML pipelines are reproducible, observable, maintainable, and robust
Model and infrastructure regressions are detected quickly and diagnosed efficiently
Common ML infrastructure capabilities become reusable platform primitives rather than being rebuilt for every AI product
The AI stack can evolve rapidly as new models, architectures, and inference techniques emerge