Senior Machine Learning Engineer
Senior Machine Learning Engineer
Senior Machine Learning Engineer
Dedrone
Senior Machine Learning Engineer at Dedrone, a leading smart airspace security company. Focus on real-time computer vision, edge deployment, and GPU-accelerated ML systems to detect, track, and classify aerial objects using C++ and CUDA.
Qualification
- Strong experience with C++ development for real-time computer vision and tracking on edge devices.
- Hands-on CUDA programming and GPU-accelerated processing for ML workloads.
- Experience building multithreaded and parallel data pipelines for ingesting, synchronizing, and processing data from networked camera systems.
- Experience integrating ML models into production pipelines, collaborating with computer vision and self-supervised learning teams (including pre/post-processing, I/O, and orchestration).
- Ability to design memory management strategies and robust data structures for large volumes of video, sensor, and metadata streams under compute and power constraints.
- Proficiency with profiling/diagnostic tools such as perf, valgrind, nvprof / Nsight to identify bottlenecks and optimize performance.
- Familiarity with deploying CV/ML systems in edge, on-premise, or cloud environments.
- Strong problem-solving, communication, and cross-functional collaboration skills.
Responsibility
- Design and implement high-performance C++ software that runs computer vision and tracking algorithms in real time on edge devices.
- Collaborate with computer vision and self-supervised learning engineers to integrate their models into production pipelines, including pre/post-processing, I/O, and system orchestration.
- Build and optimize multithreaded and parallel processing pipelines for ingesting, synchronizing, and processing data from a networked system of cameras.
- Implement and tune CUDA kernels and GPU-accelerated components to maximize throughput and minimize latency for inference, tracking, and search.
- Design robust data structures and memory management strategies for handling large volumes of video, sensor, and metadata streams under tight compute and power constraints.
- Profile and optimize code using tools such as perf, valgrind, nvprof / Nsight, and similar to identify bottlenecks and improve performance.
- Contribute to deployment and maintenance of computer vision and ML systems in production environments (edge/cloud).
- Help detect, track, and classify diverse flying objects in complex airspace environments to enhance security.
