Staff Software Engineer - Machine Learning
Hivemapper is a decentralized network of people, cameras, and apps that map the world in real time. Contributors drive with dashcams (branded 'Bee') to capture fresh street-level imagery, which is aggregated into a global map and tracked on-chain. Contributors are rewarded transparently with the HONEY token for the map data they collect.
Projects
About Hivemapper
Hivemapper operates a crowdsourced, blockchain-based mapping network in which everyday drivers use dashcam devices to capture road and street-level imagery as they go about their normal driving. This imagery is stitched together into a continuously updated, global map with coverage tracked across cities worldwide (e.g. Tokyo, Singapore, Los Angeles, Paris, New York, Austin). The network is powered by the HONEY token, which economically incentivizes contributors for collecting and verifying map data, with all contributions tracked and rewarded on-chain. Hivemapper's clients and users include companies and platforms needing fresh, real-time mapping data (the site references ride-share company Lyft using Hivemapper's community-built maps), as well as individual contributors who earn passive income ('map and earn') by driving with Hivemapper devices such as the 'Bee' dashcam, with additional fleet protection offered through a feature called 'Beekeeper'.
Skills
About the Role
You will help shape the computer vision strategy touching the full mapping stack, from hardware to data insights. You will balance state of the art techniques with practicality to produce production-grade ML solutions trained on a huge corpus of standardized data that are efficient with respect to cost and performance. You will integrate ML solutions with production systems, both at the edge and in large offline clusters.
Requirements
- Demonstrated expertise in building ML solutions, including training and deploying models, as well as integrating them into production software systems
- Hands-on experience with Image Processing and Computer Vision: Object Detection, Classification, Tracking, Localization, 3D Reconstruction, Vector embeddings, etc.
- Hands-on experience with general ML and Data Mining: Clustering, Predictions, Unsupervised Methods, Ensemble Methods, Graph Optimization, etc.
- Hands on experience with 3D reconstruction pipelines (either monocular or stereo)
- Strong programming and applied math skills (linear algebra, statistics, multivariate optimization)
- Strong software engineering fundamentals
- PhD in Computer Vision or related field (nice to have)
- Knowledge of distributed compute systems like Hadoop/Spark (nice to have)
- Experience with a variety of different ML frameworks (PyTorch, TensorFlow, OpenVINO, ONNX, etc.) (nice to have)
Responsibilities
- Help shape the computer vision strategy touching the full mapping stack, from hardware to data insights
- Balance state of the art techniques with practicality to produce production-grade ML solutions efficient in cost and performance
- Integrate ML solutions with production systems at the edge and in large offline clusters
Benefits
- Medical, dental, and vision benefits including FSA
- Family leave
- 401(k) program
- Unlimited Flex PTO
- Paid lunch
- Commuter benefits