Senior ML Engineer

Anaplan; Manchester; On-site; GBP 90,000 - 125,000; Full time

Job summary

Anaplan is hiring a Machine Learning Engineer in Manchester to move forecasting, optimization and clustering models from research into production. You will partner with data scientists to ship models, while consolidating forecasting systems into a shared backend and ensuring reliability.

You’ll lead end-to-end projects, from design to deployment, focusing on scalable pipelines, observability, and model governance.

Qualifications

• Strong professional experience building, hardening and operating ML systems in production.
• High proficiency in Python with rigorous testing, code review and CI/CD practices.
• Strong SQL and hands-on experience with a cloud data warehouse and dbt or a similar framework.
• Experience building reliable, idempotent batch pipelines with an orchestrator such as Prefect, Airflow or Dagster.
• Practical experience training and deploying PyTorch and gradient-boosted models (LightGBM or XGBoost), including GPU training.
• Experience with AWS, GCP or Azure hyperscalers.
• Experience with observability for data and ML systems (metrics, logging, drift detection, alerting) and participating in on-call.
• Ability to balance research support, platform work and operational priorities.
• Experience with feature stores, data contracts or data quality frameworks (e.g., Great Expectations, dbt tests).
• Familiarity with shadow, canary and champion/challenger deployment patterns.
• Experience with multi-tenant data platforms with strict per-customer data isolation.
• Background in forecasting, supply chain, planning or analytics applications.

Responsibilities

• Partner with Data Science R&D to turn prototypes into production-grade code.
• Refactor and consolidate forecasting pipelines into a shared backend with output parity validation.
• Extend and optimize internal ML libraries for rapid model development and deployment.
• Build automated training, retraining and batch inference pipelines with backtesting and hyperparameter tuning.
• Design idempotent, retry-safe orchestration with data validation gates and clear SLOs.
• Profile and optimize memory, compute and GPU usage; tune warehouse queries and compute for cost.
• Own experiment tracking, model registry, and data/features/model versioning with promotion gates.
• Build reusable feature pipelines with correct timing and lineage.

Skills

ML systems in production

Python

SQL

PyTorch

LightGBM / XGBoost

Cloud platforms (AWS/GCP/Azure)

Observability

Data pipelines (Prefect/Airflow/Dagit)

Tools

dbt

Dagster

Airflow

Prefect

Git / CI/CD

Job description

At Anaplan, we are a team of innovators focused on optimizing business decision-making through our leading AI-infused scenario planning and analysis platform so our customers can outpace their competition and the market.

What unites Anaplanners across teams and geographies is our collective commitment to our customers’ success and to our Winning Culture.

Our customers rank among the who’s who in the Fortune 50. Coca-Cola, LinkedIn, Adobe, LVMH and Bayer are just a few of the 2,400+ global companies who rely on our best-in-class platform.

Our Winning Culture is the engine that drives our teams of innovators. We champion diversity of thought and ideas, we behave like leaders regardless of title, we are committed to achieving ambitious goals, and we love celebratingour wins – big and small.

Supported by operating principles of being strategy-led, values-based and disciplined in execution, you’ll be inspired, connected, developed and rewarded here. Everything that makes you unique is welcome; join us and let’s build what’s next - together!

We're hiring a Machine Learning Engineer to take forecasting, optimization and clustering models from research into production. You'll partner closely with data scientists to ship new models, while hardening and scaling the pipelines we already run, including consolidating several forecasting systems into a shared backend. You'll work independently on well-scoped problems and lead projects end to end, from design doc to deployment.

Your Impact

• Research to Production: Partner with the Data Science R&D team to turn prototypes into production-grade code, shaping models for deployability.
• Refactoring & Consolidation: Refactor existing pipelines and consolidate separate forecasting systems into a shared backend, validating output parity before migrating customers.
• Shared Libraries & Frameworks: Extend and optimize internal ML libraries so data scientists can build, test and deploy models quickly and consistently.
• ML Pipelines: Build automated, reproducible training, retraining and batch inference pipelines, including backtesting, hyperparameter tuning and distributed workloads.
• Reliability & Hardening: Design idempotent, retry-safe orchestration with data validation gates, graceful fallbacks and clear SLOs for freshness and on-time delivery.
• Scale & Performance: Profile and remove memory, compute and GPU bottlenecks, and tune warehouse queries and compute for cost as we scale.
• Model Lifecycle (MLOps): Own experiment tracking, the model registry, and versioning of data, features and models, with automated promotion gates, shadow runs and fast rollback.
• Feature & Data Platform: Build reusable feature pipelines with point-in-time correctness, training and inference consistency, and clear lineage.
• Observability & Model Quality: Monitor data drift, prediction drift and model accuracy, own pipeline alerting, take part in on-call and lead blameless postmortems.
• Automation & Multi-tenancy: Make pipelines configuration-driven for low-touch customer onboarding, with strict per-customer data isolation and infrastructure as code.
• Technical Excellence: Set the testing strategy for ML code, improve CI/CD, write design docs and runbooks, and mentor teammates.

Your Skills

• Strong professional experience building, hardening and operating ML systems in production.
• High proficiency in Python with rigorous testing, code review and CI/CD practices..
• Strong SQL and hands-on experience with a cloud data warehouse and dbt or a similar framework.
• Experience building reliable, idempotent batch pipelines with an orchestrator such as Prefect, Airflow or Dagster.
• Practical experience training and deploying PyTorch and gradient-boosted models (LightGBM or XGBoost), including GPU training.
• Experience with AWS, GCP or Azure hyperscalers.
• Experience with observability for data and ML systems (metrics, logging, drift detection, alerting) and participating in on-call.
• Ability to balance research support, platform work and operational priorities.
• Experience with feature stores, data contracts or data quality frameworks (e.g., Great Expectations, dbt tests).
• Familiarity with shadow, canary and champion/challenger deployment patterns.
• Experience with multi-tenant data platforms with strict per-customer data isolation.
• Background in forecasting, supply chain, planning or analytics applications.

Our Commitment to Diversity, Equity, Inclusionand Belonging (DEIB)

We believe attracting and retaining the best talent and fostering an inclusive culture strengthens our business. DEIB improves our workforce, enhances trust with our partners and customers, and drives business success. Build your career in a place where diversity, equity, inclusion and belonging aren’t just words on paper – this is what drives our innovation, it’s how we connect, and it contributes to what makes us a market leader. We believe in a hiring and working environment where all people are respected and valued, regardless of gender identity or expression, sexual orientation, religion, ethnicity, age, neurodiversity, disability status, citizenship, or any other aspect which makes people unique. We hire you for who you are, and we want you to bring your authentic self to work every day!

We will ensure that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process, perform essential job functions, and receive equitable benefits and all privileges of employment. Please contact us to request accommodation.

Privacy & AI Notice

C andidate data processed during our recruitment activities is handled in accordance with our Candidate Privacy Notice. This may include the use of artificial intelligence or automated tools to assist our team in evaluating qualifications.