Spatial AI Engineer

BigGeo is the Spatial Cloud.

We help companies manage and access the worlds spatial data.

Any size any slice any insight.

Delivered in seconds.

Were building something that hasnt existed before: a new layer of the internet where the where and when behind every decision is instantly clear programmable and actionable. Our platform removes the complexity that has kept spatial data locked in silos for decades and replaces it with speed precision and control.

Were a Calgary-based company early and moving fast with real customers real infrastructure and a clear point of view on where the world is going.

Most companies are spatially blind. They know what their data says but not where or when things actually happen. That gap costs real money creates real risk and limits what AI can actually do in the physical world.

BigGeo exists to close that gap.

Were not building another tool. Were building the rails that connect the planets moving data to the systems that run the world. Thats a big problem and it takes people who care about doing things right not just fast.

• The problem is real and the category is open. Were not competing for the middle of an existing market were defining a new one. Your work shapes what the category becomes.
• Your fingerprints are on the architecture. Were at the stage where the decisions you make today become the foundation tomorrow. What you ship matters.
• We run on clarity not politics. We move with purpose. No bureaucratic drag no HiPPO decisions just a team that agrees on the mission and gets to work.
• Youll grow fast because the problems are hard. Spatial data at scale is a genuinely difficult domain. If you want to be stretched youll be stretched.
• Were building for longevity. Were not chasing hype cycles. Were building infrastructure the kind that compounds in value over time and earns the trust of the companies that depend on it.

The Spatial AI Engineer builds the systems that let AI models applications and intelligent agents understand and reason about the real world through spatial data. You will design and implement machine learning systems that operate directly on spatial datasets inside The Spatial Cloud turning raw location and time data into intelligence that applications and AI agents can act on in seconds.

This role sits at the intersection of machine learning spatial computing and large-scale data infrastructure. You will build the models pipelines and inference services that make spatial intelligence operational: not research artifacts sitting in notebooks but production systems answering real questions at global scale.

You will work alongside Core Systems Engineers building the Spatial Cloud platform data platform engineers managing global spatial datasets and product teams shipping spatial intelligence capabilities to developers and enterprises. The problems are hard the datasets are enormous and the impact is visible because what you build is used in real-world environments.

If you want to build AI systems that reason about the physical world and shape a new category of infrastructure as it takes form this is the place to do it.

As a Spatial AI Engineer you will contribute to and own systems that include:

• Spatially-aware machine learning models that incorporate geometry location and temporal context as first-class inputs.
• AI-powered spatial analytics and pattern detection systems that find signal in global-scale geospatial data.
• Spatial reasoning systems that understand how places movements and events relate across space and time.
• Training and evaluation pipelines for spatial AI models including dataset management labeling workflows and reproducible experiments.
• Real-time spatial inference services that deliver model outputs to applications and agents with low latency at scale.
• APIs and services that let developers applications and AI agents query spatial intelligence directly from The Spatial Cloud.

• Design train and iterate on machine learning models that operate on spatial and spatio-temporal datasets.
• Build models that detect patterns relationships and anomalies across geospatial signals from dense urban data to sparse global datasets.
• Experiment with spatial reasoning approaches that incorporate location geometry and temporal context as explicit features not afterthoughts.
• Evaluate model accuracy calibration reliability and operational behavior against real production workloads.

• Build pipelines for ingesting cleaning transforming and preparing spatial datasets for machine learning.
• Manage training datasets versioning and evaluation frameworks with the rigor of a production system.
• Ensure spatial data pipelines are scalable reliable and observable as datasets and usage grow.

• Deploy models into production systems used by applications developer APIs and AI workflows.
• Build inference services capable of delivering spatial insights in real time with predictable performance characteristics.
• Integrate AI capabilities directly with The Spatial Clouds data and compute infrastructure so intelligence lives where the data does.

• Optimize AI models and inference pipelines for large spatial datasets and high-throughput query patterns.
• Make deliberate trade-offs across latency cost accuracy and operational complexity.
• Ensure spatial AI systems scale with growing datasets growing users and growing use cases without constant rework.

• Partner with Core Systems Engineers building the spatial compute layer and data platform engineers managing large spatial datasets.
• Work closely with product teams to translate real customer problems into model behavior and service design.
• Own systems end to end: design build ship measure and improve.

In this role that means:

• Using modern coding assistants (such as Claude ChatGPT Cursor and Copilot) to accelerate implementation refactor work debugging and testing.
• Using AI to accelerate ML experimentation: drafting training scripts generating evaluation frameworks exploring alternative model architectures and stress-testing your own assumptions.
• Using AI for data exploration and engineering: generating pipeline scaffolding writing SQL reasoning over schemas and summarizing datasets before committing to modeling approaches.
• Using AI agents and workflows to automate repetitive engineering tasks so more of your time goes to high-impact design modeling and systems work.
• Bringing strong judgment about when AI output is good enough when it isnt and when to push back. Your name goes on the system not the tools.

• 3 to 7 years of experience building machine learning systems or AI-driven data products in production.
• Bachelors degree in Computer Science Engineering or a related field.
• Strong programming experience in Python and deep familiarity with modern machine learning frameworks (PyTorch TensorFlow or equivalent).
• Experience building and deploying production machine learning models and inference systems not just notebooks or prototypes.
• Hands-on experience working with large datasets and distributed data processing pipelines.
• Solid grasp of machine learning evaluation model lifecycle management and responsible experimentation.
• Demonstrated ability to collaborate across engineering data and product teams and to own outcomes not just tickets.
• Working knowledge of SQL and comfort operating in cloud-native environments.
• Experience using AI development tools (such as Claude ChatGPT Cursor and Copilot) to accelerate engineering work.

• Experience working with geospatial or location-based datasets in a production context.
• Background in spatial analytics geospatial modeling or spatial statistics.
• Familiarity with spatial indexing techniques (such as H3 S2 quadtrees R-trees) and common geospatial data formats (GeoJSON GeoParquet PMTiles FlatGeobuf or similar).
• Experience building AI systems that interact with structured data platforms data warehouses or lakehouse architectures.
• Experience with real-time inference systems streaming pipelines or event-driven architectures.
• Experience with performance-critical programming in Rust or Go.
• Contributions to open-source AI geospatial or data infrastructure projects.

First 30 days:

Onboarded onto the Spatial Cloud stack datasets and current modeling systems. Running local and cloud experiments against real spatial data and contributing code reviews. Clear picture of the current AI roadmap key systems and the people you work with most closely.

First 60 days:

Shipped meaningful improvements to an existing model pipeline or inference service. Led design discussions on at least one model or system component and have a clear point of view on trade-offs. Helping shape how AI capabilities get exposed to product surfaces and developer APIs.

First 90 days and beyond:

Owning one or more production spatial AI systems end to end: model data pipeline evaluation and inference service. Driving measurable improvements in accuracy latency cost or coverage against well-defined baselines. Influencing the spatial AI roadmap including which problems we choose to solve and how. Known inside and beyond the engineering org as a technical leader in spatial AI at BigGeo.