16 of 16 Anomaly Detection Jobs in the South East

analyse integration pipeline telemetry and identify inefficiencies, bottlenecks, or redundant processes. Identify and Encourage Cost and Efficiency Savings AI Collaborate with DevOps to introduce anomaly detection models to proactively identify unusual patterns in deployment behaviour, system performance, or test failures. Collaborate with DevOps and QA teams … tools (Jira, Azure DevOps). AI Skills Experience with AI-driven test optimisation, intelligent prioritisation, and synthetic test data generation. Hands-on use of anomaly detection models in CI/CD pipelines. Comfortable with AI-powered telemetry, observability, and root-cause analysis tools. NICE-TO-HAVE Experience ...

considerations. Familiarity with modern data infrastructure and architecture (APIs, pipelines, cloud platforms), with exposure to AI/ML or LLM-based enrichment solutions for anomaly detection and automation. Exposure to Agile methodologies such as Scrum or Kanban. Awareness of emerging trends in Private Markets data, including ...

business development. Mastery of enterprise architecture components, business/IT principles, and organisational processes. Experience applying AI/ML across corporate functions (e.g., financial anomaly detection, HR attrition prediction, procurement spend analytics). Competencies Exceptional analytical, planning, and organisational capabilities, with strong situational awareness and political acumen. ...

deep learning techniques to drive innovation in the FinTech domain. Hands-On Modelling & Delivery Build, train, validate, and deploy ML solutions across risk modelling, anomaly detection, personalisation, optimisation, and predictive analytics. Lead experimentation cycles, champion best practices, and ensure models are production-ready. Partner with Machine Learning ...

triaging and introduce automation for high-volume workflows Design and build Gen AI LLM/VLM solutions for self driving car behavior analysis and anomaly detection Proactively monitor and assimilate best practices from within Alphabet and the broader industry to develop a Reinforcement Learning from human preference ...

scalable and robust product architecture. Define and evolve chart-of-accounts mapping, ensuring alignment with industry-standard frameworks where applicable. Extend error- and outlier-detection logic, annualisation processes and export capabilities (Excel, API and additional formats as required). Partner with customers and internal stakeholders to understand pain ...

safety tools (e.g., Responsible AI Toolbox, Deepchecks) Familiarity with Azure AI Foundry and LLM compliance testing frameworks Prompt injection testing and AI behaviour anomaly detection This is a great role, and an awesome time to join this business as they expand their artificial intelligence team. For more ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...

answers - avoid stochastic elements or require fixed random seeds for exact reproducibility Base problems on real business challenges: customer analytics, risk assessment, fraud detection, forecasting, optimization, and operational efficiency Design end-to-end problems spanning the complete data science pipeline (data ingestion → cleaning → EDA → modeling → validation → deployment considerations … comparison corrections Causal inference: propensity score matching, difference-in-differences Complex ETL pipeline logic and multi-source data integration Missing data imputation and outlier detection algorithms Feature engineering: encoding, interactions, dimensionality reduction Time Series & Forecasting Trend decomposition and seasonality detection Stationarity testing and autocorrelation calculations Forecast ...