Job Title: Machine Learning Engineer

Location: Remote, US-only

Company: Atomic Maps; info@atomicmaps.io

The Role

We're seeking a Machine Learning Engineer with strong production ML experience to own the full ML lifecycle, bring models to production, and help us scale our geospatial AI systems. This is a hands-on technical role where you'll build, deploy, monitor, and maintain models in production. You will deploy clean, testable, containerized, and scalable inference workflows to Atomic Flow that serve our customers across imagery, video, and 3D data. 

You will work closely with the infrastructure and data engineering teams with a focus on operationalizing our ML and MLOps systems and ensuring they run reliably and effectively in production. This collaborative setup lets you focus on what you do best: developing robust, well-engineered ML systems, fine-tuned for customer use cases, and ensuring they perform reliably at scale. 

It's an ideal opportunity for a mid-level engineer with solid ML fundamentals who wants to deepen their production ML skills and gain hands-on MLOps experience in a supportive, fast-moving startup environment.

Responsibilities

• Design and implement scalable, reproducible ML pipelines for training, retraining, and deploying models

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

• Own the model lifecycle from training and validation through deployment, monitoring, and retraining using MLflow, Kubeflow, or similar tools

• Develop and deploy containerized inference services for large-scale geospatial and computer vision workloads

• Collaborate with data engineering, infrastructure, and product teams to ensure smooth integration and measurable impact

• Stay current with advances in ML and evaluate practical opportunities for adoption

Key Skills & Experience

Required

• Strong Python skills with experience in writing clean, maintainable, and testable production-grade code with libraries like PyTorch, TensorFlow, etc.

• Experience building, fine-tuning, and deploying ML models for imagery and video data (e.g., detection, segmentation, or feature extraction) using YOLO, SAM, etc.

• Experience with one or more MLOps tools (MLflow, Kubeflow, or similar) for experiment tracking, deployment, and monitoring

• Experience writing production-grade code (modular packages, reusable libraries, and, automated testing, CI/CD integration) for ML pipelines and models

• Excellent problem-solving and communication

Nice to Have

• Experience with geospatial or computer vision workflows

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

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

• Experience with containerized workflows using Docker

• Experience with orchestration platforms like  Argo Workflows, Airflow, or Prefect

• Familiarity with Infrastructure as Code tools like Terraform

• Experience with OpenSearch or ElasticSearch

Why Join Us

• 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 and pick up the latest technologies and foundational models as they are released

• You are ready to help shape our ML engineering practices, improving how we build, deploy, and maintain models in production

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.