**About Satellogic**Satellogic is a vertically integrated Earth Observation satellite and data company. We design, manufacture, and operate our own fleet of satellites, the Aleph-1 constellation, which delivers high-frequency, high-resolution imagery plus full-motion video.Earth Observation imagery and data are key to monitoring change at scale, informing critical decisions, and ultimately helping solve the world’s most pressing problems. Our mission is to democratize access to this information, making it affordable and available for those who need it across a wide range of industries, from climate monitoring and agriculture, to energy, infrastructure and many more. We want to do our part in building a world where every organization is prepared for the challenges of tomorrow.With a growing team of almost 400 employees spanning 18 countries, Satellogic is a diverse group of purpose-driven professionals across software development, satellite engineering, operations, data science, manufacturing, and sales. We are excited to grow and welcome team members who push the limits, get things done, and never stop learning—all while being humble, honest, and empathetic.**About the team**The Data Product team is responsible for building out the future of Satellogic’s core image processing technologies, spanning the reconstruction and calibration of satellite imagery from physical data to the semantic understanding of our planet. The scale of the problem requires us to process massive amounts of data and process it reliably, accurately and in a timely manner - we believe that these challenges will present exciting opportunities for innovation and efficient and robust infrastructure is at the core of our ability to deliver on our vision.**About the position**As the "Principal Computer Vision / Perception Platform Engineer" you will:- Work side-by-side with the computer vision and deep learning engineers on the team and reporting directly to the VP of Product Development Imagery Platform, you'll be responsible for accelerating the research and productization of Satellogic’s core imagery products.- Advocate for tools and technologies to accelerate research organize and build out systems to make data accessible to the team identify common threads in team activities and standardize experimental workflows.- Emphasize metrics-driven research.- Distribute neural network training across fleets of compute servers to leverage massive datasets.- Optimize machine learning inference on mobile devices for near real-time use.- liaison between product development and platform/infrastructure teams at in the Data Products team to facilitate rapid deployment and iteration of products**Location**Remote work from anywhere between UTC-5 and UTC+3 time zones. Satellogic’s office locations include Buenos Aires, Barcelona, Montevideo, Cordoba (ARG)**About you**You will be excited to navigate the complexities of satellite image processing and the compute resources involved in accurately reconstructing the surface of the earth from collections of images.You will also understand that robust handling of data feeding machine learning algorithms is crucial to the final product and this needs to be observable and quantifiable in its impact to the business.If processing terabytes of data, scaling up inference and reconstruction to create value for users is something you are passionate about, let's talk!**Experience**- 10+ years of software engineering experience. Experience building scalable backend services or data processing pipelines. Solid understanding of ML/DL fundamentals and production ML workflows.- Good understanding and experience in technologies such as Image capture, 3D sensing, CGI, SLAM, AR, HDR, color correction.- Several years of experience architecting, building, developing and scaling ML and/or Computer Vision systems.- Having implemented and deployed a variety of machine learning pipelines production environments would be a strong plus.**Skills**- Ability to write performant, well-tested, production-ready Python code.- Developing Python bindings or cloud interfaces to tooling written in C++ using Docker/Kubernetes/Terraform/AWS/GCP.- Deploying trained models for inference on cloud infrastructure and addressing issues of compute autoscaling.- Training machine learning models using PyTorch or Tensorflow.- Building deep learning pipelines including: Metrics collection, experiment tracking and hyperparameter tuning (e.G. W&B;, Comet.ML, DVC.Org) ML lifecycle platform utilization (e.G. SageMaker, Metaflow, MLflow).- Distributed training (e.G. DeepSpeed, Horovod).- Optimizing model inference e.G. via quantization/pruning.**Diversity Commitment**Satellogic values diversity and inclusion and is an equal opportunity employer. We are convinced that hiring and developing top talent from around the world for any given discipline will drive innovation, generate new solutions, and deliver