Our mission is to understand what we’re doing on, and to, Earth. We do this through our cloud-based SaaS platform, Orbital Insight GO, pulling in multiple sources of raw data from the world’s sensors – including millions of daily satellite images and connected device pings – combined with proprietary AI to analyze economic, social, and environmental trends at scale. By making the Earth “searchable” our customers have been able to illuminate supply chains, track global commodities, monitor illegal deforestation, and further national security. We are building the best AI team in the world to innovate, implement, deploy, and support these capabilities.
We are data detectives and our job is difficult because although we have Big Data, we exist in a persistent state of spatio-temporal data starvation. The work is fast-paced, highly iterative, and continuously trading off between what works and what’s best. Along with our team of data scientists, you’ll work with product managers, sales... and software engineers to build data-driven products and solutions. If you enjoy working with data to build products and solve hard problems in creative ways, you will fit right in.
As a part of the Model Engineering team, you will work within a cross-functional team that is responsible for the full algorithm development process, all the way from human annotation to integration with the platform. Your role as a Senior Machine Learning Infrastructure engineer means that you will be part of a small group of software engineers for our Computer Vision and Data Science sub-teams and will be responsible for owning infrastructure for experiment tracking, model training/inference, dataset version control, and imagery annotation campaign creation and data extraction. You will also work closely with our Platform and Product Engineering teams, as well as our Content team, to guide high-level engineering of the platform.
This position will be based in our Palo Alto, CA office. Currently, Orbital Insight is fully remote (working from home) until the end of the year, due to COVID.
Responsibilities
Develop workflows, pipelines, and tools for faster and more efficient imagery annotation, model training, model deployment, and continual monitoring of computer vision and data science algorithms
Build tools and stand up new technologies to further develop our R&D capabilities
Design, implement, and deploy a scalable training and inference system to support the development of new CV algorithms to integrate into our multi-source, geospatial analytics platform
Develop and deploy microservices/REST APIs for machine learning model inference using Docker + Kubernetes
Mentor other members on your team with code reviews, design discussions, and new technologies
Collaborate with engineers on our Platform and Product Engineering teams
Work with DevOps to support our training infrastructure (on prem and in cloud)
Qualifications
Bachelors or Masters degree in a STEM field (e.g., computer science, machine learning, statistics, physics, engineering)
4+ years industry experience in related role and 5+ years experience with Python (or similar language)
4+ years of experience working with evolving ML ecosystems (e.g. kubeflow, mlflow, etc.) and solved related infrastructure challenges around model hosting, serving, and inference pipelines
4+ years of experience working with cloud computing platforms like AWS or Azure, as well as containerization software (Kubernetes, Docker, etc.)
2+ years of experience utilizing strong analytical and problem solving skills, including software debugging, and solving the challenges of developing computer vision algorithms
2+ years of experience in deep learning and related toolkits (e.g., Tensorflow, Pytorch) is a major plus
2+ years of experience with Spark/Scala is a major plus
See something wrong with this listing?
Contact support