Principal Machine Learning Engineer
London Stock Exchange Group19 days ago
Nottingham, United Kingdom or London, United KingdomStaff+
Responsibilities
- Define the end-to-end ML architecture for the matching platform, including data pipelines, training workflows, inference runtimes, telemetry, and monitoring.
- Lead AWS SageMaker adoption across training, processing, model registry, monitoring, deployment, retraining, approvals, and rollback orchestration.
- Architect scalable feature pipelines, feature-store standards, data-quality guardrails, validation schemas, and lakehouse-oriented feature architecture.
- Lead the design of ranking, scoring, similarity, calibration, confidence-threshold, and optimization strategies for matching models.
- Establish explainability standards and regulator-ready reason-code patterns using SHAP or equivalent frameworks.
- Design low-latency, high-throughput inference services, secure cross-account IAM patterns, telemetry, SLOs, and reliability strategies.
- Define monitoring for feature drift, concept drift, performance degradation, data integrity, privacy, and compliance.
- Set ML security and governance standards covering encryption, PII handling, model cards, lineage, auditability, reproducibility, versioning, and traceability.
- Lead validation and performance strategies using golden datasets, behavioral tests, benchmarks, A/B testing, shadow deployments, canary rollouts, and controlled experiments.
- Mentor engineers, review complex technical designs, influence product and architecture decisions, and set long-term engineering direction.
Requirements
- Proven experience architecting and delivering production machine learning systems at scale in enterprise environments.
- Deep expertise with AWS SageMaker, including training, processing, pipelines, endpoints, and model registry, plus complementary AWS services.
- Expert-level Python and experience with ML frameworks such as PyTorch, TensorFlow, and XGBoost.
- Strong expertise in MLOps automation, CI/CD for ML, model lifecycle management, and production deployment.
- Advanced experience designing explainability systems, reason codes, governance artifacts, drift detection, telemetry pipelines, observability, and model QA.
- Experience with low-latency inference architectures, real-time model serving, cross-account IAM, data minimization, and PII-safe design.
- Ability to influence architecture, mentor senior engineers, approve complex designs, and establish long-term technical standards.
- Experience with feature stores, ranking, search relevance, entity matching, similarity modeling, or multi-account AWS ML platforms is preferred.
- Knowledge of distributed training, GPU or accelerator optimization, and scaling strategies is preferred.
- Bachelor’s degree in a STEM subject such as mathematics, physics, engineering, or computer science is required; a master’s degree or PhD or equivalent STEM experience is desirable but not essential.
Benefits
- Healthcare, retirement planning, paid volunteering days, and wellbeing initiatives are offered.
- The company provides an inclusive, collaborative, and creative culture with equal-opportunity employment and reasonable accommodation support.
- Employees can participate in fundraising and volunteering through the LSEG Foundation.
Categories