Location: San Francisco, CA (preferred) Type: Full-Time Team: Research/Engineering

Overview

At Blok, we’re building the simulation engine powering the next generation of adaptive software. Our multi-agent system predicts how different types of users will respond to digital experiences before any code is shipped. Product teams use Blok to simulate onboarding flows, test risky design changes, and de-risk product bets without waiting weeks for live traffic.

We’re hiring a highly skilled Data Scientist to help us scale out our product. You’ll work across engineering and research - and focus on improving the foundational data science infrastructure - from ingestion pipelines to experimentation frameworks. Ideally, you’ll have deep expertise in statistical modeling, machine learning, and data engineering practices, with the ability to design, implement, and scale data-driven solutions.

🌍 Our Vision

Software today is static. We believe the future is adaptive interfaces that evolve in real time based on the user's behavior, intent, and context.

Blok is building the behavioral foundation model to power that shift - starting with a simulation engine that helps product teams understand, predict, and personalize user experience before launch. In the long term, we’re building toward a world where software feels more like a conversation than a fixed experience.

🔧 What You'll Be Doing

• Build and optimize data pipelines (ETL/ELT) across SQL/NoSQL systems, ensuring reliability and quality of large-scale event/log data.
• Apply statistical modeling, causal inference, and ML to analyze user behavior, design experiments, and generate insights.
• Develop predictive, generative, and clustering models (embeddings, anomaly detection, time-series) to power simulations and personalization.
• Deploy and scale models in cloud environments (AWS/GCP/Azure) with containerized workflows (Docker/Kubernetes).
• Create monitoring and evaluation pipelines to track performance, detect drift, and ensure fairness and reproducibility.

✅ What We’re Looking For

• Strong proficiency in Python for data science and ML workflows.
• Expert in large-scale unstructured data manipulation.
• Solid foundation in statistics, probability, and causal inference.
• Hands-on experience with machine learning frameworks (PyTorch, TensorFlow, Scikit-learn).
• Experience with cloud platforms (AWS, GCP, or Azure) and containerized deployment (Docker/K8s).
• Proven ability to design and interpret A/B tests, analyze experiment data, and implement feedback loops.