Applied Scientist

Striv is a startup building at the intersection of wearable sensing, AI, and real-time feedback for movement and performance. We are based in Boston, focused on sports and human performance, and are building products that turn continuous sensor data into meaningful coaching and health insights.

We have completed multiple rounds of funding, shipped early products to 50+ countries, and received support from top Olympic athletes. We are now in a fast iteration and growth stage, expanding into more sports and movement scenarios.

Our team is highly technical, with members from MIT, Harvard, and leading tech companies. We care deeply about building real products on top of hard sensor, modeling, and product problems.

• Build robust, interpretable signal and metric pipelines from long-horizon time-series sensor data
• Develop reliable methods for modeling baseline, variability, anomaly/deviation, and longer-term state changes
• Analyze and model data across users, contexts, devices, and environments, handling normalization, distribution shift, drift, and consistency
• Build personalization systems that learn what is normal for each individual and identify meaningful changes earlier
• Explore modeling approaches for continuous sensor data, including forecasting, anomaly detection, risk modeling, representation learning, and user modeling
• Design evaluation frameworks, regression tests, and analysis pipelines to validate whether model changes actually improve product outcomes
• Work closely with engineering and product teams to productionize algorithms, define interfaces and data fields, and support rapid iteration

• 3–7 years of experience in data science, machine learning, or applied modeling
• Strong experience in at least one of the following:
• time-series data, sensor data, wearable/IoT data, telemetry, or large-scale behavioral logs
• Strong fundamentals in Python, statistics, and machine learning
• Comfortable working with real-world data issues such as noise, missingness, weak labels, distribution shift, and device variation
• Experience with or strong interest in longitudinal modeling, sequential modeling, heterogeneity, and personalization
• Strong engineering sense: able to write maintainable code and care about evaluation, reproducibility, versioning, and iteration speed
• Able to independently drive work from problem framing → analysis → modeling → validation → productization

• Experience with wearables, physiological signals, IMU, pressure data, PPG, telemetry, or anomaly detection
• Experience taking models from offline research/analysis into production
• Experience with A/B testing, monitoring, regression validation, or experiment design
• Experience in one or more of the following:
• forecasting, risk scoring, user modeling, personalization, representation learning
• Strong interest in sports, health, smart devices, or consumer products
• Experience with edge deployment, on-device inference, model compression, or low-latency systems

• High-value real-world sensor data with fast feedback loops
• Opportunity to define core capabilities in sensing, personalization, evaluation, and product intelligence
• Tight collaboration across hardware, software, algorithms, and product
• Real ownership in a 0→1 and 1→N company-building environment
• Compensation: competitive and flexible based on fit