Job Description

About the Company

We are working with A1, a company incubated and backed by BJAK, whose mission is to build the next generation of AI-native applications that fundamentally change how people communicate and get things done. A1's first application, AI Email Triage, reimagines email by moving users from reading and writing emails to learning from and approving AI-completed work-- making it efficient, smart and delightful.

A1's core capabilities are Agentic AI - AI that can reason through multi-step workflows and use external tools to complete tasks; Permission-Based Actions - AI that always asks for approval before taking actions such as sending emails or updating your calendar, keeping users in control; Context & Memory - AI remembers user preferences and past context to deliver increasingly personalised, accurate, and consistent assistance over time.

BJAK is the largest insurance platform in Southeast Asia with presence in Japan, United Kingdom and growing.

Role Summary

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.

Responsibilities

• 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

Key Performance Indicators

• 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

Our Ideal Candidate

• Has strong software engineering fundamentals and experience building production systems
• Has experience building ML infrastructure, platforms, or production machine learning systems
• Has experience with model deployment, inference, evaluation, or data pipelines
• Has strong understanding of distributed systems and system reliability
• Able to write clean, maintainable, production-quality code
• Comfortable working in ambiguous, fast-moving environments
• Takes ownership, open to experimentation and continuous improvement
• Has the following 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