ML Software Engineer
Indexed description
This is a hands-on, high‑ownership role within a growing group working closely with algorithm developers. The work spans Python and C++, ML infrastructure, model integration, performance optimization, and production delivery.
- The role includes working on-site at our Jerusalem office several days per week.
- Lead end-to-end development of features - from design and implementation to integration, testing, and deployment
- Build ML pipelines for data-based diverse dataset creation and efficient model inference.
- Design data selection and sampling strategies to ensure coverage of rare and critical scenarios.
- Partner with algorithm teams to translate model weaknesses into data curation criteria.
- Develop validation and diagnostics to measure dataset quality—not just pipeline health but training effectiveness.
- Integrate neural network models into C++ production systems, including runtime, data flow, and pre/post‑processing.
- Bring models from research/prototype stage into robust, production‑ready deployments.
- Optimize runtime performance (latency, memory, and throughput) in resource‑constrained environments.
- Contribute to deployment flows (e.g., model conversion, profiling, optimization).
- Build and improve CI/CD pipelines, automated testing, and development workflows.
- B.Sc. in Computer Science, Software Engineering, or equivalent.
- 3+ years of hands-on C++ development experience.
- 3+ years of hands-on Python development experience, including the PyData stack (NumPy, Pandas).
- Experience working in Linux environments.
- Strong motivation to work closely with deep learning algorithms and production of AI systems
- Interest in neural network deployment on edge devices, including inference runtimes, performance optimization, and model integration.
- Proven ability to work across team boundaries (algorithms, infra, product).
- Strong motivation to work on production AI systems and deep learning integration.
- Interest in edge deployment, inference runtimes, and performance optimization.
- Experience with autonomous-driving datasets or perception pipelines.
- Background in 3D geometry and/or strong mathematical foundation.
- Experience with workflow orchestration tools (Airflow, Argo).
- Familiarity with data curation techniques (e.g., active learning, hard example mining, distribution balancing).
- 2+ years in data engineering or backend systems with large‑scale data (production environments).
Create a free Caio profile to unlock more results and save your role and location preferences.
Unlock free search