Machine Learning Engineer - Auckland

About Auror

At Auror, we’re empowering the retail industry to tackle theft and Organised Retail Crime, a $150 Billion problem globally. It’s high volume crime that’s increasingly organised in nature and is putting people, retailers, and communities at risk every day.

Founded in New Zealand 11 years ago, we’re working with some of the best and largest retailers in the world across the US, Canada, Australia, New Zealand, and the UK.

Auror is connecting people and intelligence to reduce crime. We’re using technology for good.

In partnership with our leading retail partners, we need people with the passion, determination, and innovation required to overcome one of the world’s largest problems. If you’re looking to make a difference with and for the people dedicated to stopping crime, for good, then we want you on our team.

We're also embracing the potential of AI to supercharge our impact—whether that's enhancing the way we detect trends, support our customers, or improve internal workflows. As a company, we're committed to responsibly incorporating AI into how we work and what we build, and we encourage all Aurors to be curious about how AI can elevate their work, regardless of role or function.

We’re on a mission to give retailers unparalleled visibility into what’s happening across their business, turning real-time data into actionable intelligence that helps them stay one step ahead.

Today, more than 13,500 retail stores and 50,000 retail professionals around the world rely on our platform. The scale and complexity of our data presents an incredible opportunity to uncover patterns, predict outcomes, and build intelligent products that make a real difference in the fight against retail crime.

We're looking for an innovative Machine Learning Engineer who is excited by the challenge of transforming large-scale, multi-modal data into smart, impactful features used by retailers globally. You'll work alongside a talented team of data scientists, engineers, and product leaders to build production‑grade machine learning systems that deliver real‑world outcomes.

You’ll have the freedom to own the entire machine learning lifecycle, from identifying opportunities and designing solutions, through experimentation, model development, deployment, and continuous improvement. You'll be working with a modern cloud‑native data and ML platform built on technologies such as Dagster and Apache Iceberg and kubernetes, and industry‑leading machine learning tooling, such as pytorch and scikit‑learn, giving you the opportunity to solve challenging problems at scale with a contemporary stack.

This isn't a research role. It's about applying machine learning to real‑world problems, building practical solutions that help retailers prevent crime, protect their teams, and operate more effectively. Your work will move beyond notebooks and prototypes into production systems that create measurable impact every day.

As we work with sensitive data across multiple countries, legal frameworks, and privacy regimes, responsible innovation is at the heart of everything we do. We've developed a comprehensive Responsible AI Framework and a set of guiding principles that ensure we build technology thoughtfully, ethically, and with trust at the forefront. You'll play an important role in helping us push the boundaries of what's possible with AI while ensuring we always do the right thing.

I joined Auror with the mission of harnessing data science and Artificial Intelligence to make a meaningful difference to reducing retail crime. My passion lies in leveraging emerging technologies and best practices to design and optimize data‑driven solutions that empower organizations to unlock the full potential of their data assets.

I thrive in collaborative environments with curious, motivated individuals who embrace continuous learning, enjoy working with modern technologies and methodologies, and are eager to explore innovative and ethical ways to use data.

You’ll work with one of the most unique retail crime datasets in the world, spanning structured data,…