Senior Data Scientist

Description

Upstream is looking for an experienced Senior Data Scientist to join our rapidly growing data science team, focusing on creating ML-driven prediction and anomaly detection models. As a Senior Data Scientist, you will lead the analysis of large (often massive) datasets, develop models and algorithms to meet customer needs. You will be working closely with other data scientists, data engineers, product managers and domain experts to improve our automotive purpose-built data management platform, focusing on vehicle quality, cybersecurity and API security use cases.

As a Senior Data Scientist at Upstream, you’ll play a pivotal role in driving innovation and shaping the future of ML-based solutions in automotive quality and cyber security. You’ll work on challenging datasets, develop advanced models, and see your work integrated into impactful, real-world applications.

Your work will directly enhance the safety and quality of advanced automotive systems and cybersecurity solutions. At Upstream, we prioritize talent development, offering you opportunities to learn, innovate, and grow in a collaborative environment.

This role is full-time and is Herzliya, Israel based.

Responsibilities

• Conduct in-depth research on large and diverse automotive live streaming tabular datasets, preprocess the data, as well as extract and present key insights
• Search and craft indicative features that will enhance the value of ML models
• Explore, design and deploy cutting-edge ML models or algorithms solutions for prediction purposes and anomaly detection 
• Collaborate closely with domain experts and peers to research and implement models and algorithm flows that best fit requirements 
• Partner with our data engineering and development teams to devise innovative solutions for productization 
• Encourage collaboration and knowledge-sharing within the data science team

Requirements

• 6+ years of relevant industry experience in data science or machine learning
• Education: MSc in Math / EE / CS / Statistics OR BSc in one of the disciplines above and 10+ years of substantial, hands-on experience in data science or a closely related domain – demonstrating expertise equivalent to that typically acquired through formal advanced education
• Demonstrated research expertise in the tech industry or published academic papers
• Profound understanding and hands-on expertise in mathematics, statistics, machine/deep learning, and data mining
• Expertise in data science pipelines is essential, including data cleansing, feature engineering, and model tuning
• Strong coding and software engineering experience focusing on advanced proficiency in Python, especially in data science libraries such as Pandas, Polars, NumPy, SciPy, Scikit-learn, and others 
• End-to-end experience in leading the development of AI/DS/ML products or features, including managing their deployment in production environments, whether through direct integration or by using existing APIs
• Demonstrated experience in working streaming data (including sequential/time series) and implementing corresponding algorithms/models in a production environment, whether in batch processing or real-time scenarios
• Solid experience in deep learning, utilizing platforms such as TensorFlow, Keras, PyTorch, etc. 
• Proficiency in SQL 
• Strong communication skills, with the ability to convey ideas and share knowledge effectively 
• Independent and quick learner, capable of developing independently 
• A valuable team player who cooperates well 
• Experience thriving in a dynamic work environment 

Upstream is an equal opportunity employer. All candidates for employment will be considered without regard to race, color, religion, sex, national origin, physical or mental disability, veteran status, or any other basis protected by applicable federal, state or local law.