Spire Global is a space-to-cloud analytics company that owns and operates the largest multi-purpose constellation of satellites. Its proprietary data and algorithms provide the most advanced maritime, aviation, and weather tracking in the world. In addition to its constellation, Spire’s data infrastructure includes a global ground station network and 24/7 operations that provide real-time global coverage of every point on Earth.
As part of the drive to better serve our customers and deliver higher volumes of more insightful, lower-latency data, Spire is continuously increasing the level of spacecraft autonomy and on-board processing of raw data. Spire has been launching various high-performance computing devices to enable this. This role will contribute to the development and implementation of machine learning models to run on these computing devices for a variety of applications, including data size reduction, RF signal detection and pattern recognition, image processing, autonomous operations, telemetry analysis etc.
As an engineer at Spire, you’ll move fast, iterate quickly, and solve global problems. You might be the right fit if you love exciting technical challenges, hate getting bored, and enjoy collaborating with engineers who are changing the way the world thinks about space, satellites, and data.
Responsibilities of your role:
- Applying machine learning techniques to develop and evaluate models to improve the performance of satellite subsystems in various application areas (e.g. software defined radio, image processing, telemetry analysis, data size reduction)
- Contributing to the implementation of models on target computing hardware
- Integrating and improving 3rd party machine learning models
- Validating the on-orbit performance of the models and related subsystems and providing support to the operations of your systems
- Representing your work to internal and external reviewers and customers
- 5+ years of work experience
- Experience and aptitude in developing hypotheses and machine learning solutions for problems interacting with physical systems (e.g. large noisy existing datasets, data collected directly from hardware platforms, sensor systems, imaging systems etc.)
- Experience with machine learning techniques as implemented on target hardware (e.g. ARM Linux systems, Xilinx FPGAs, Nvidia Jetson platforms, TPUs/VPUs).
- Knowledge of a variety of deep learning architectures like CNN, RNN/LSTM etc.
- Experience with common analysis tools available in Python (such as NumPy and scikit-learn) and deep learning frameworks (such as TensorFlow, PyTorch and Keras) with the ability to apply these frameworks towards real-world problems
- Degree or equivalent background in quantitative statistics, computer science, math or other technical fields
- Demonstrated working experience applying machine learning techniques and advanced data science techniques to problems
- Experience with machine learning algorithms specifically targeted for digital signal processing, Earth Observation or other geospatial products
- Familiarity with heterogeneous programming (CUDA, OpenCL)
- Experience developing software using a compiled language (such as C or /Python/Rust)
- Basic real-time programming/software design and development.
- Basic understanding of communications theory, digital radio communications, signal processing and signal property inference
- Basic understanding of computer vision, image processing and machine-learning based image classification
- Experience in a high-reliability industry (Automotive, Aerospace, Defense, Medical) or an embedded industry (e.g. IoT, Mobile Phones, Distributed Sensor Networks, Industrial Automation etc.)
- Experience working with geospatial datasets
- Experience in debugging complex software issues
Spire is Global and our success draws upon the diverse viewpoints, skills and experiences of our employees. We are proud to be an equal opportunity employer and are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, marital status, disability, gender identity or veteran status.