Machine Learning Lead

Job Title: ML Lead

Location: Remote, US-only

Company: Atomic Maps

About Us: We are a small, dynamic geospatial software and data consulting startup. Our team is dedicated to building Atomic Flow (our geospatial data platform) and Atomic Lens (our map-based app) to unify unstructured data under a single search, discovery, and inspection engine.

The Role: We’re seeking a Machine Learning Lead to design and operate our ML lifecycle at scale. This role blends hands-on technical work with leadership: you’ll architect feedback loops, guide best practices in MLOps, and ensure our models are continuously improving in production. You’ll be the bridge between our labeling pipelines, data engineers, and customer-facing solutions. As the ML Lead, you’ll also set the direction for our ML practice, mentor teammates, and help us grow a strong, sustainable capability in machine learning.

Responsibilities: 

  • Own the design and implementation of scalable ML pipelines for training, retraining, and deploying models

  • Build automated feedback loops that incorporate labeled data from imagery and other modalities

  • Manage model lifecycle using MLflow, Kubeflow, or similar tools (from experiment tracking to production deployment)

  • Develop and publish containerized inference engines for large-scale geospatial and computer vision workloads

  • Stay current with advances in multimodal ML (imagery, video, point cloud, radiance field, 3D spatial AI) and guide Atomic’s adoption

  • Collaborate with engineers and product teams to align ML capabilities with customer use cases

  • Establish best practices for MLOps, reproducibility, and scalability across the organization

  • Mentor and guide teammates and shape the future of Atomic's ML strategy.

Key Skills & Experience:

  • Experience taking models from research to production, with a focus on MLOps

  • Comfortable deploying container-based models with Docker/Kubernetes

  • Hands-on experience with MLflow, Kubeflow, or similar model management frameworks

  • Familiarity with multimodal model training (imagery, video, point cloud)

  • Strong Python skills with experience in ML frameworks (PyTorch, TensorFlow, etc.)

  • Solid understanding of data structures, SQL, and cloud storage patterns

  • Excellent problem-solving, communication, and leadership skills

Nice-to-Have Skills:

  • Experience with geospatial or computer vision workflows

  • Familiarity with cloud platforms (AWS, GCP, or Azure) and GPU-based training environments

  • Exposure to 3D data processing (e.g., point clouds, meshes, radiance fields, 3D tiles)

  • Knowledge of spatial AI applications such as map-building from sensor data (HD maps, AR/VR, robotics)

We Encourage You to Apply If:

  • You’re passionate about building ML systems that last beyond the first deployment

  • You enjoy tackling hard technical problems in a collaborative environment

  • You’re curious and eager to experiment with cutting-edge multimodal ML techniques

  • You want to set the tone for a growing ML practice and mentor others along the way

Don’t meet every single requirement? That’s okay. If you’re motivated, smart, and excited about shaping the future of ML for geospatial data, we want to hear from you.

Atomic Maps is an equal opportunity employer. We do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.

Apply Now