Senior Machine Learning Engineer

Carbon Mapper, Inc. Senior Machine Learning Engineer Remote
· Full time

Help ensure our core data products meet a reliable baseline of quality, latency, and cost as we scale.

Senior Machine Learning Engineer

About Carbon Mapper

Carbon Mapper is a non-profit organization based in Pasadena, CA with the mission to drive greenhouse gas emission reductions by making methane and carbon dioxide data accessible and actionable. We leverage remote sensing technology to detect, pinpoint, and quantify methane and carbon dioxide (CO 2 ) emissions at the scale of individual facilities. All of our methane and CO 2 data is made publicly available for non-commercial use on our Carbon Mapper Data Portal to provide decision makers with the information they need to prioritize and take mitigation action.

Carbon Mapper also works with stakeholders and decision makers to fill data gaps, lead on cutting edge science, collaborate to drive reductions, and advance education and insights on emissions globally. To do this, we work with partners to leverage a constellation of satellites. Data from these satellites will offer the next major step in scaling up the organization's robust data portal featuring thousands of direct observations of global methane and CO 2 super-emitters.

As a Senior Machine Learning Engineer on our Data Operations team, you'll help ensure our core data products meet a reliable baseline of quality, latency, and cost as we scale. You'll use operational metrics to pinpoint bottlenecks and quality gaps, then partner with peer teams to fix them through machine learning, automation, and process improvement. You'll bring deep ML expertise to a domain-heavy problem space (remote sensing, plume detection, and infrastructure mapping) and connect that expertise directly to the operational outcomes our data products depend on.

• Design, develop, and deploy deep learning and machine learning models for remote sensing imagery analysis, classification, and segmentation. Applications include plume detection, hyperspectral data processing, and infrastructure mapping.
• Identify and integrate remote sensing and other spatial datasets (RGB imagery, basemaps, weather data, GIS inventories) to develop and improve models, using AI-assisted tooling to accelerate data exploration and profiling.
• Bring current best practices in remote sensing and machine learning to cross-functional discussions on product design and implementation.
• Mentor and provide technical guidance to less experienced team members, fostering skill development in ML, data engineering, and remote sensing across the Data Operations team.
• Lead significant data-quality initiatives end-to-end, from problem definition through deployment, collaborating with members of the Data Operations, Science, and Engineering teams.
• Design and build automation and tooling that reduce manual effort and improve the consistency and throughput of core data products.

• Advanced degree or equivalent experience in Earth Science, Atmospheric Science, Remote Sensing, Computer Science, Statistics, Artificial Intelligence, or a related field.
• Experience building statistical and machine learning models using remote sensing datasets, with applied expertise in deep learning approaches (e.g., transformers) and frameworks such as PyTorch, Tensor Flow, or similar.
• Demonstrated ability to use remote sensing imagery in deployed ML systems for detection of atmospheric gases, weather conditions, natural or agricultural ecosystems, or land use/land cover.
• Comfort adopting AI tools across the ML workflow, including AI-assisted coding and AI-supported model development, testing, and evaluation, with a clear perspective on when and how these tools add value and where careful review and engineering judgment are needed to verify outcomes.
• Experience designing and evaluating production ML systems, defining model performance metrics and validation strategies that reflect real operational conditions.
• Track record of diagnosing model errors, bias, drift, and failure modes in production, and translating those findings into concrete model or pipeline improvements.
• Experience deploying, monitoring, and maintaining models in production, with a focus on observability, reproducibility, and sound model-lifecycle practices.
• Experience developing scalable training and inference pipelines that balance performance, latency, and…