• Design, prototype, and deploy machine learning algorithms related to perception, state estimation, and behavior planning (Python). • Identify, implement, and respond to meaningful metrics that affect vehicle behavior. • Serve as a technical expert for the team balancing short-term deliverables and long-term directions. • Collaborate closely with experts across disciplines to work across the entire stack to improve the reliability and performance of the system.

• Design, develop, and deploy machine learning and artificial intelligence solutions that drive product innovation and business impact • Work closely with engineering, data, product, and business teams to build scalable models, production-grade ML systems, and intelligent applications • Handle the full machine learning lifecycle, from data preparation and feature engineering to model training, deployment, monitoring, and continuous improvement • Combine strong technical depth with practical problem-solving skills and collaborate effectively with both technical and non-technical stakeholders in a remote environment aligned with U.S. time zones

• Step is looking for an experienced Data Scientist to build and deploy Machine Learning models for all things Risk and Fraud. • You’ll design, develop, and deploy machine learning models to enhance our Risk and Fraud detection systems. • You’ll take the lead in the Risk/Fraud area, providing technical direction and helping shape team’s strategy. • You’ll use SQL to efficiently fetch, transform, and manipulate data. • You’ll write production-grade code to deliver robust machine learning solutions. • You’ll apply statistics to guide experiments, determine appropriate sample sizes, and evaluate model performance. • Partner with Operations Team to quickly respond to rapidly evolving events.

• Integrate open-source and third-party models into our inference platform • Lead fine-tuning initiatives (LoRA, adapters, PEFT, domain adaptation) • Optimise inference workloads for latency, batching, memory efficiency, and throughput • Benchmark model quality vs cost vs performance across modalities • Improve inference startup times and stability under high load • Build evaluation frameworks and internal tooling for model validation • Work closely with Infrastructure and Backend teams on scalable serving systems • Monitor production performance and drive continuous optimisation • Mentor engineers and help raise the ML engineering bar across the team