Company Description

Property intelligence is reshaping how the world understands the built environment, and Nearmap is driving that. We put powerful aerial imagery, AI-driven analytics, and geospatial tools into the hands of the people who plan, build, insure, and govern the places we all live and work. Our technology turns property uncertainty into decisive action, and our culture brings out the best in the people who build it.

Job Description

The maps that planners, insurers, and governments rely on to understand the physical world don’t update themselves — someone has to build the systems that turn raw aerial imagery into ground truth. That’s this team.

This role is all about translating R&D from other parts of the Nearmap AI & Computer Vision team into data and ultimately, answers. You will be a core contributor to the algorithmic systems for creating conflated Map Data

products.

Conflation is the process of combining multiple data observations about the world into a single, cohesive map that prioritises usability, practicality, and a straightforward representation of real world objects. Input data sources include aerial imagery (multiple surveys over time, 2D, 3D, multi-angle, and captured by multiple providers), other geospatial sources such as property data, permit data or suitably licensed open data sets. A key challenge is to provide transparency of data provenance and accuracy, while abstracting away as much complexity as possible.

We design, build, and operate software systems that take petabytes of data to transform aerial imagery to insight. Our technology stack is based on the python scientific libraries and traverses machine vision deep learning technology such as Pytorch, and GIS tools such as GEOS, Shapely and GeoPandas/GeoPolars. We work mostly in python for speed of development and occasionally drop down to compiled libraries when we need to care about performance.

A typical day

You might spend a morning profiling a conflation pipeline that’s producing unexpected artefacts near property boundaries, pair with a CV researcher in the afternoon to understand what their model’s confidence scores actually mean for downstream data quality, then finish the day reviewing a colleague’s PR on a new spatial indexing approach. Agentic coding tools like Claude Code are a normal part of how we work — not a novelty, but a practical accelerant for the kind of exploratory, iterative work this role involves.

Ways of working

This is a fully remote role, open to candidates located on the East Coast of Australia (Melbourne, Sydney,  Brisbane). The team operates with daily stand- ups, close collaboration, and a culture of open communication — expect regular pair programming, drop-in calls, and genuine team involvement in your work.

Qualifications

We’re after exceptional candidates, who have real world experience but are eager to learn.

Essential

• Demonstrated 5+ year history working in a numerical field: e.g. applied maths, physical sciences, computer vision, geospatial analysis.
• A demonstrated ability to produce high quality production numerical code with a focus on business outcomes.
• Programming & tech environments: ability to code in scientific python, using a Linux environment, and git for source control.
• Machine learning fundamentals: appreciation of core ML concepts including regularisation, hyperparameter optimisation, and validation methods.
• Scientific approach: follow the scientific method of formulating hypotheses, and applying statistical tests to validate them.
• Engineering approach: follow best practices in modern software engineering, applying them to build robust, scalable machine learning systems.
• Strong approach to systems thinking, whilst remaining pragmatic.
• Commitment to software engineering principles for scientific python, a keen eye for clean code, and a passion for robustness and correctness.

Highly desirable

• Working with large data sets, where data doesn’t fit into memory, and requires multiple nodes to compute efficiently.
• A scientific mindset of formulating hypotheses, and applying statistical tests to validate them.
• Working in a cloud-native environment using highly scalable compute.
• Experience with operationalizing numerical applications and workflows.
• Scale: working on machine learning problems applied to image and geospatial data.

Personal attributes

• ML Engineering is a team sport; communicate well, share knowledge, and be open to taking on ideas from anyone in the team.
• While extensive knowledge of theory and best practices are highly valued, pragmatism wins over elaborate theory when it comes to shipping products that work.

Tertiary qualifications

• Formal education in a field related to numerical science (Bachelor’s degree in computer science, engineering, statistics, physics, etc.). Applicants with a Masters/PhD will fit in well within the team, but are by no means necessary — we’re more interested in what you can do!

Additional Information

• In your application, include one sentence about a specific geospatial or numerical problem you’ve found genuinely interesting, bonus points if it relates to what you have learnt about Nearmap. This helps us understand how you think.

Some of our benefits

Nearmap takes a holistic approach to our employees’ emotional, physical and financial wellness. Some of our current benefits include:

• Quarterly wellbeing day off - Four additional days off annually for your ‘YOU’ Days
• Wellbeing and technology allowance
• Annual flu vaccinations
• Hybrid flexibility for this role
• Nearmap subscription (of course!)
• Stocked kitchen with access to all the snacks you need
• In-office lunch every Tuesday and Thursday at our Sydney CBD office
• Showers available for anyone cycling to work or lunchtime gym-goers!

Working at Nearmap

We move fast, we care about craft, and we’re proud of what we’re building. If you’re energised by turning hard problems into real-world impact, we’d love to meet you.

If you can see yourself working at Nearmap and feel you have the right level of experience, we invite you to get in touch.

Read the product documentation for Nearmap AI:

https://docs.nearmap.com/display/ND/NEARMAP+AI

For a deep dive into Nearmap AI, listen to AI Systems Senior Director Mike Bewley on the Mapscaping podcast https://mapscaping.com/blogs/the-mapscaping-podcast/collecting-and-processing-aerial-imagery-at-scale

Thanks, but we got this! Nearmap does not accept unsolicited resumes from recruitment agencies and search firms. Please do not email or send unsolicited resumes to any Nearmap employee, location or address. Nearmap is not responsible for any fees related to unsolicited resumes.