Machine Learning Engineer — Aerial Image Classification

Raad Labs; California (MO); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Competitive equity

Health, dental & vision

Remote-first

Home office budget

Generous paid time off

Learning & travel budget

Job summary

Raad Labs is seeking a Machine Learning Engineer for aerial image classification. The role focuses on building and shipping detection and classification models across high-resolution aerial imagery, with emphasis on production-grade PyTorch pipelines and scalable deployment.

You will own dataset curation, augmentation strategies, and training infrastructure, plus deployment to clusters and edge devices. The position offers remote-first work from anywhere in the U.S. and a strong equity package.

Qualifications

• 4+ years building and shipping computer vision models to production.
• Experience with overhead or industrial imagery is preferred.
• Deep, practical PyTorch experience and fluency in modern detection literature and toolchain.
• Strong Python engineering habits; training code should be production-grade.
• Experience with deployment optimization (TensorRT, ONNX Runtime, quantization) is a strong plus.

Responsibilities

• Train, evaluate, and ship detection and classification models for aerial inspection use cases.
• Own the full loop—from dataset curation to deployment on cluster and edge targets.
• Build evaluation harnesses with per-class, per-region, and per-sensor breakdowns.
• Collaborate with the edge team to quantize and prune models for on-device inference.

Skills

PyTorch

Python

Model optimization

Tools

TensorRT

ONNX Runtime

Job description

# Machine Learning Engineer - Aerial Image ClassificationDepartmentEngineeringLocationUSA - West Coast (PST) or Mountain preferredTypeFull time · RemoteSalary$180k-$230k## About RAADRAAD operates a global aerial intelligence network. Clients order high-resolution site imagery, thermal inspections, and 3D data through our platform; our pilot network captures it; and our processing and vision-model pipeline turns raw imagery into structured, georeferenced answers - often within hours. We run our own hardware end to end: capture fleets in the field, GPU processing clusters we built ourselves, and deployments that span public cloud, our own data centers, and secure on-prem environments inside client facilities.We're growing fast across every region we operate in, and we're hiring people who want to help scale systems and operations that already work - and make them work at ten times the volume.## The roleRAAD's vision models are the reason clients come back: asset detection, defect classification, change detection, and volumetrics run automatically on every dataset the moment it lands. Our detection stack is built on the YOLO family and custom classification heads, trained on one of the largest proprietary corpora of close-range aerial imagery in the industry - and it's growing every day. We're expanding the ML team to cover more asset classes, more industries, and more geographies.## What you'll do* Train, evaluate, and ship detection and classification models (YOLO-family, ViT-based classifiers, segmentation) for aerial inspection use cases: roofs, solar arrays, transmission hardware, pipelines, flare stacks.* Own the full loop - dataset curation, augmentation strategy for aerial-specific challenges (scale variance, nadir vs. oblique, thermal/RGB fusion), training infrastructure, and deployment to both cluster and edge targets.* Build evaluation harnesses that catch regressions before clients do, with per-class, per-region, and per-sensor breakdowns.* Work in Python across the stack: PyTorch, ONNX/TensorRT export, and the tooling that keeps annotation, training, and deployment moving.* Partner with the edge team to quantize and prune models for on-device inference.## What you'll bring* 4+ years building and shipping computer vision models to production, ideally detection/segmentation on overhead or industrial imagery.* Deep, practical PyTorch experience and fluency in the modern detection literature and toolchain.* Strong Python engineering habits - your training code is software, not a notebook graveyard.* Experience with model optimization for deployment (TensorRT, ONNX Runtime, quantization) is a strong plus.## Benefits & perks### Competitive pay & equityStrong base salary plus meaningful equity - everyone shares in what we're building.### Health, dental & visionComprehensive coverage for you and your dependents, tailored to your country.### Remote-firstWork from anywhere in your role's region. Async-friendly, documentation-driven culture.### Gear & home office budgetTop-spec hardware and a budget to build a workspace you actually enjoy.### Generous time offFlexible PTO plus your local public holidays. We expect you to use it.### Learning & travelAnnual learning budget and team offsites - plus real field time with the operations your work powers.## Apply for this role