About Us
We are Ocado Group, and we're bringing world-class automation to online grocery. Our Ocado Smart Platform (OSP) combines cutting-edge robotics, AI, and IoT within our advanced CFCs (Customer Fulfilment Centres). We've mastered the single pick, transforming online delivery for our global partners. Join us and be part of a team pushing the boundaries of retail technology.
About the Team
Smarties is the Data Science and intelligent personalisation team within the Ecommerce stream at Ocado Technology — the part of Ocado Smart Platform (OSP) that powers the end-customer shopping experience. We build the prediction, ranking, and recommendation capabilities that power smart features across OSP and that product teams integrate into customer-facing journeys.
We are a cross-craft team combining data scientists, software engineers, and ML engineers — a mix of skills that lets us work across the full stack of a smart feature, from data and modelling to production systems.
Our mission is to make smart feature development scalable and self-serve. We turn the hard parts of "smarts" — prediction, ranking, personalisation — into reusable building blocks, proven on our own products first, so that over time any product team can build intelligent features using our platform and our support.
We own and operate a broad portfolio of Data Science systems in production:
- Checkout walk personalisation
- Order prediction and recommendations
- Customer intelligence
- Search and browse ranking
- Recipe discovery
- Web analytics data pipeline that underpins measurement across Ecommerce
Job Purpose
A Senior ML Engineer in Smarties brings the engineering perspective to a cross-craft team: raising the bar on how ML systems are built, not just how they perform.
This means championing industry best practices across the full ML lifecycle — from experimentation and model design through to serving, monitoring, and cost management — and translating that expertise into systems that are reliable, testable, scalable, and maintainable in production.
Key Responsibilities
1. Influence – Be an Individual with Positive Impact
- Actively teach, coach, and create opportunities for others to share and develop expertise — both within the team and across the wider organisation.
- Act as a technical leader and consultant on ML within the team's domain, raising the quality bar on how ML problems are defined and solved.
- Work across craft boundaries: collaborate effectively with data scientists and software engineers, helping the team function as one cross-craft unit rather than parallel silos.
- Promote realistic commitments at the team level; openly share trade-offs, uncertainties, and technical risks.
- Represent ML thinking in conversations with product managers, data analysts, and consuming engineering teams.
2. Execution and Delivery – Get Value Out of the Door
- Take ownership of the full ML lifecycle — from problem framing and data exploration through training, evaluation, deployment, and monitoring (MLOps) — on production systems that directly affect revenue and customer experience.
- Make key design decisions on ML/AI components within our portfolio, weighing technical, cost, and product implications explicitly.
- Break work into incremental, reversible steps that deliver value early and reduce risk.
- Handle production incidents and degradations effectively, diagnosing root causes and resolving them at the right speed.
- Deliver with a high degree of autonomy; contribute to technical direction within the team.
- Contribute to both the ongoing health of production systems and the emergence of reusable platform building blocks — extracting from real problems, not building speculatively.
3. Insights – Solve Real Problems
- Analyse production ML systems, identify failure modes, and drive improvements grounded in data.
- Design and implement well-defined experiments to validate hypotheses, from offline evaluation to live AB tests.
- Seek the root of the problem being solved; translate business requirements into correctly scoped ML problems.
- Proactively surface data-driven insights to technical and non-technical audiences.
- Contribute to raising data quality standards across the team's pipelines — treating reliable, well-understood data as a foundation for all ML work.
4. Strategy – Keep an Eye Toward the Future
- Apply sufficient domain knowledge to make good design decisions across the team's ML portfolio.
- Identify opportunities to simplify the live system — reducing support burden, compressing costs, and building leverage (for example, replacing several bespoke models with a single configurable engine).
- Apply appropriate testing and de-risking principles, especially when working on systems with direct business impact.
- Investigate and resolve production issues, raising awareness where these stretch beyond the team.
- Collaborate with the Engineering Manager and Data Science leads on the technical direction of the platform.
- Understand consuming teams' needs well enough to design building blocks that serve them without creating new dependencies.
Benefits: What’s in it for you?
- Standard benefits: life insurance, private health care [Luxmed], Multisport card, lunch vouchers, company share programs, and assistance for everyday worries and serious health problems.
- Learning opportunities: access to the Learnebly platform and LinkedIn Learning, English classes, and a book library.
- Parental support: additional +10 days maternity / +20 days paternity leave, funding for nurseries and kindergartens.
- Hybrid model: 2 days/week in the office and flexibility to work from almost any location for up to 30 days a year.
- Office perks: centrally located offices with car and cycling parking, and home office equipment provided.
- Career growth: a clear career path with opportunities to rotate between projects, teams, domains and roles under the guidance of highly skilled senior colleagues.
- High engineering culture: unique software engineering culture with a high level of test coverage and agile environment read about our tech stack and engineering practices across Ocado Technology.
- Speaker community: public speaking training and support for preparing presentations at conferences or meetups, including our own Ocado Technology Meetups.
- Passions groups: running, cycling and more.
- Annual celebrations: carnival, summer parties, family picnics, or kid’s days.
- Gross Monthly Pay range: 23 600 zł—29 900 zł PLN.
Required Qualifications
- ML Engineering in Production
- Demonstrated experience owning the full Data Science lifecycle — data, training, evaluation, deployment, serving, and ongoing operations — on production systems, not just prototypes.
- Experience monitoring data drift, training/serving skew, and model degradation.
- Strong understanding of production discipline, beyond modelling alone.
- Data Fluency
- Strong working knowledge of data processing tools, such as BigQuery (SQL), pandas, Dataflow, or equivalent technologies.
- Ability to treat data quality as a first-class concern.
- ML Fundamentals
- Fluency in supervised and unsupervised learning, ranking models, recommendation systems, evaluation metrics, overfitting, and model selection.
- Cloud Platform Experience
- Practical experience with GCP, including Vertex AI, BigQuery, and Dataflow.
- Experience with AWS, as both cloud platforms are used across the company's infrastructure.
- Python
- Strong production-grade Python skills.
- Ability to work comfortably in a codebase where models and services are consumed by other engineers.
- Technical Leadership
- Experience leading the technical design of ML projects.
- Ability to articulate technical trade-offs and drive decisions within a team.
Valued Qualifications
- LLM-Based Systems
- Experience with RAG, structured generation, evaluation, and cost management.
- Familiarity with GCP/Vertex AI or similar platforms.
- ML Infrastructure and Platforms
- Experience building or contributing to shared ML infrastructure or internal platforms, such as feature stores, serving layers, and shared pipelines.
- Recommendation Systems and Personalisation
- Experience with recommendation systems, personalisation, or search ranking at scale.
- Cross-Craft Collaboration
- Experience working in a cross-craft team alongside software engineers and data scientists.
- A/B Testing and Experimentation
- Understanding of A/B testing methodology and experimentation platforms.
- Java
- Familiarity with Java, as the company's model-serving layer is built on Java services.
