We are hiring a senior individual contributor to join our Data Science team. This is a hands-on role for someone who can take ownership of the full solution, from understanding the problem and building the required data pipelines to developing the model, deploying it, and keeping it reliable in production. You should be comfortable working across data, code, infrastructure, and monitoring independently.
The domain is genuinely hard: noisy sensor and telemetry data, weak and delayed labels, enormous scale, and physical systems that fail in complicated ways. We use whatever technique the problem calls for, from classical machine learning and survival analysis to our own patent-pending deep learning architectures and agentic flows already running in production.
The team moves quickly and operates with a startup mentality: high ownership, short decision paths, and a strong bias toward action. When we encounter a difficult problem, we do not stop at we cant. We ask, How can we?
Moving fast does not mean cutting corners. It means combining resourcefulness and practical judgment with scientific rigor, engineering quality, and production reliability.
We also have proprietary methods for validating results against ground truth, so the feedback loop is real: when a solution works, it ships. You will see your work in production and understand its impact on real fleets.
What youll do
Own projects end to end: stakeholder discussions, problem framing, data exploration, modeling, validation, deployment, and post-launch monitoring.
Turn ambiguous or partially defined business needs into clear, practical, and measurable solutions.
Build predictive and prescriptive models over large-scale vehicle telemetry, diagnostics, and fault data.
Design, build, and maintain scalable, reproducible, and well-tested data pipelines over billions of daily data points.
Build and operate the workflows required for training, validation, inference, and ongoing evaluation.
Take responsibility for getting solutions into production, including automated testing and deployment, environment configuration, monitoring, and troubleshooting.
Choose the right tool for each problem, from gradient boosting and survival analysis to deep architectures over raw signals-and clearly explain your decisions.
Design evaluations that reflect reality, use our proprietary validation methods, and challenge metrics that tell a comfortable but misleading story.
Develop and integrate agentic and LLM-based flows that explain findings, recommend actions, and build the relevant evals.
Investigate failures across data, models, workflows, and production systems.
Present findings, trade-offs, and results clearly to business stakeholders and executive leadership.
Raise the technical bar through reviews, mentorship, and shared standards, as a senior IC, not a people manager.
דרישות:
MSc in Computer Science or an engineering-related quantitative field, such as Electrical Engineering, Statistics, Physics, or Applied Mathematics. A PhD is an advantage.
At least eight years of industry experience in a related data science or machine learning role.
Proven experience taking machine learning solutions to production, not only building prototypes and notebooks, but deploying, monitoring, maintaining, retraining, and troubleshooting what you shipped.
Strong experience building reliable, performant, and well-tested data pipelines over very large datasets.
Strong experience with Spark, distributed computing, SQL, and modern big data platforms. Databricks experience is a significant advantage.
Practical experience with automated testing and deployment, cloud-based systems, workflow orchestration, monitoring, and production troubleshooting.
Experience delivering LLM or agentic applications to production, including evaluation, guardrails, and cost and latency trade-offs.
Strong foundations across statistics, experimental design, classical machine learning, and modern deep learning.# המשרה מיועדת לנשים ולגברים כאחד.