• Design and implement causal inference frameworks and statistical models to measure the impact of interventions, evaluate system performance and uncover opportunities for improvement. • Build, evaluate and iterate on causal ML models that power high-stakes decisions, applying best practices across the full model lifecycle from feature engineering to production deployment. • Develop frameworks to analyze tradeoffs between competing objectives (accuracy, coverage, user experience and operational cost), and propose strategies to improve overall effectiveness. • Build strong relationships with cross-functional partners across Product, Design, Engineering, Operations, and Analytics to drive collaboration and innovation. • Communicate learnings to leaders and stakeholders in a clear, compelling manner that drives informed, data-driven decision-making. • Think strategically about how to scale and evolve data science capabilities within your domain, contributing to the long-term vision for how science drives platform outcomes.

• Identify high-impact business opportunities through data exploration and model prototyping, and translate business problems into scientific formulations. • Analyze structured and unstructured data to uncover meaningful insights and craft actionable proposals that help shape strategy. • Build and deploy production LLM/ML models that directly contribute to the launch of data-driven products, leveraging AI tools to enhance efficiency and impact. • Build strong relationships with cross-functional partners across Product, Design, Engineering, Operations, and Analytics to drive collaboration and innovation. • Communicate learnings to leaders and stakeholders in a clear, compelling manner that drives informed, data-driven decision-making. • Contribute to the long-term vision for how science drives platform outcomes within your domain.

Role Description Brego is an automotive technology company using AI and data analytics to help dealerships, lenders, and other industry partners make better vehicle valuation, pricing, and risk decisions. As a Lead Data Scientist, you will take ownership of the AI and machine learning capabilities behind products that influence high-value pricing and risk decisions. This is a hands-on technical leadership role where you will be responsible for designing, building, deploying, and continuously improving production machine learning systems from end to end. You will own the full lifecycle of models, from feature engineering and training through deployment, monitoring, retraining, and ongoing optimisation, working independently while collaborating closely with engineering and product teams to deliver measurable business impact. Responsibilities - Own the end-to-end lifecycle of production machine learning models, from problem definition through deployment and ongoing optimisation. - Design, build and deploy artificial neural network and machine learning models for vehicle valuation, pricing and other analytics. - Take responsibility for production model performance, reliability and long-term maintenance. - Evaluate model performance and improve predictive accuracy across production models. - Develop and maintain automated retraining pipelines to keep models effective over time. - Monitor deployed models, investigate issues and implement improvements to ensure models remain accurate and reliable. - Design and run experiments, track results and use data to drive model improvements. - Work closely with engineering and product teams to integrate models into production systems and deliver business value. Qualifications - 5+ years of experience building and deploying machine learning models in production environments. - Strong experience developing and training neural networks for real-world applications. - Strong experience with the Python data science ecosystem, including pandas, NumPy and scikit-learn. - Hands-on experience with PyTorch or TensorFlow. - Strong understanding of machine learning, statistics, and model evaluation methodologies. - Experience taking machine learning models from concept through deployment and ongoing production ownership. - Experience evaluating model performance, improving predictive accuracy, and maintaining retraining pipelines, model monitoring, and experiment tracking. - Experience with feature engineering and working with large, real-world datasets. - Experience writing clean, maintainable, production-quality Python code. - Experience with SQL for data analysis and data manipulation. - Experience deploying ML workloads in cloud environments. - Ability to independently own technical projects and make sound engineering decisions with minimal supervision. - Strong problem-solving skills with the ability to investigate complex data and modelling challenges. - Strong communication skills, with the ability to explain technical concepts to both technical and non-technical stakeholders. - Experience collaborating with software engineers, product managers, and data engineers. - Eligible to work in the UK. Nice to have - Experience in the automotive industry or with vehicle data. - Experience in pricing, forecasting, risk modelling, or other predictive analytics domains. - Experience with MLOps tooling and infrastructure. - Experience building automated data and model pipelines. - Experience mentoring or providing technical leadership to other data scientists or engineers. Benefits - Competitive salary of £90,000 - £110,000 per year, depending on experience. - Private healthcare. - Pension scheme. - Fully remote role with flexible working hours. - Working from home allowance. - Choice of Apple MacBook Pro or high-spec Windows workstation. - Learning and progression opportunities. - Optional access to our Silverstone office. The team usually meets there around one day per week, but attendance is entirely optional. - High levels of ownership and autonomy with the opportunity to shape the company’s AI strategy. - Collaborative, low-bureaucracy engineering culture that values autonomy, integrity and innovation. - Regular company social events. - 25 days annual leave plus 3 additional days between Christmas and New Year.

Role Description Praescient Analytics is seeking multiple Data Scientists to support advanced fraud analytics and investigative initiatives for a federal oversight organization. These positions will develop, test, validate, and deploy innovative analytical solutions that help identify fraud, waste, abuse, and mismanagement across large-scale federal benefit programs and other government-funded initiatives. Working as part of a multidisciplinary analytics team, Data Scientists will leverage statistical analysis, machine learning, data visualization, entity resolution, and risk modeling techniques to transform large, diverse datasets into actionable intelligence supporting investigators, auditors, and government decision-makers. The ideal candidate is a technically strong, mission-focused data scientist who enjoys solving complex analytical problems while collaborating with investigators, business analysts, data engineers, forensic accountants, and government stakeholders. Key Responsibilities - Develop, test, validate, and maintain fraud detection and program integrity analytics. - Design analytical rules and methodologies to identify fraud indicators, anomalies, suspicious activity, and emerging risks. - Perform exploratory data analysis, feature engineering, model development, validation, and performance evaluation. - Analyze structured and unstructured data from multiple public, non-public, commercial, financial, and government data sources. - Collaborate with Data Engineers to prepare and optimize data for analytics. - Support entity resolution, anomaly detection, predictive analytics, and risk scoring initiatives. - Produce dashboards, reports, visualizations, and analytical products that support investigative decision-making. - Document analytical methodologies, assumptions, validation results, and technical findings. - Participate in Agile delivery activities including sprint planning, demonstrations, peer reviews, and iterative model development. Qualifications - Must have experience with Fraud Analysis. - Three (3) or more years of professional experience in data science, applied analytics, machine learning, statistics, fraud analytics, or a related quantitative field. - Strong programming experience using Python and SQL. - Experience developing and validating analytical models. - Experience analyzing structured and unstructured datasets. - Experience documenting analytical methodologies and technical findings. - Strong analytical reasoning and problem-solving skills. - Excellent written and verbal communication skills. Preferred Qualifications - Experience in fraud detection, fraud prevention, financial crime analytics, or program integrity. - Familiarity with federal benefit programs, grants, loans, healthcare, unemployment insurance, emergency assistance, disaster relief, or other public-sector programs. - Knowledge of risk modeling, anomaly detection, entity resolution, predictive analytics, and statistical modeling. - Experience with cloud analytics environments such as Azure Databricks, Microsoft SQL Server, Microsoft Fabric, Azure Data Lake Storage (ADLS), Power BI, Git repositories, or Lakehouse architectures. - Experience working with public, non-public, commercial, financial, or cross-agency datasets. - Skills in data visualization and dashboard development. - Experience in Agile software development and analytics teams. - Understanding of enterprise data governance, metadata management, and data quality best practices. Benefits - Competitive salary based on qualifications and experience. - Comprehensive, Company paid healthcare for you (We pay your premiums and deductibles). - 401(k) with company match. - Travel & performance incentives. - 3 weeks paid time off (plus Federal Holidays). - $5K annual training allowance. - $500 book allowance. - Tuition reimbursement program.