Wolt’s Personalization team is responsible for creating a tailored experience for Wolt’s customers across their shopping journey, helping them to discover the best restaurants, dishes or items that match their culinary and shopping preferences across multiple premises such as Discovery, In Venue or Checkout.
We build and maintain the recommendation systems that power these experiences in real time for millions of users across more than 30 markets. For example, the team is responsible for the models that rank restaurants in Wolt’s Discovery page, venues in Wolt’s category pages or items in Wolt’s in-venue and cart premises. It also personalises other components in Wolt’s shopping experience such as brands, banners or food categories that are relevant entry points for our customers to explore Wolt’s assortment.
The team is multidisciplinary, including software engineers, applied scientists, ML Engineers. Together, we own the ML-powered personalisation stack, integrations across Wolt’s platform, and the systems that turn customer behavior and data into meaningful, dynamic and engaging experiences.
What you’ll be doing
As a Software Engineer in Wolt’s Personalisation (ML-driven) team, you will:
Build and scale backend systems that serve and operationalise machine learning models powering real-time personalisation and recommendations for millions of users.
Work closely with ML Engineers and Applied Scientists to productionise models, translate offline experiments into reliable online services, and continuously improve model impact.
Own and evolve the real-time recommendation and inference stack, focusing on low-latency, high-throughput model serving under heavy traffic.
Design APIs and data flows that enable feature delivery, inference, experimentation, and monitoring in production.
Improve system reliability, scalability, and observability to ensure ML-powered experiences perform consistently in real-world conditions.
Contribute to the team’s technical direction, improving architecture, developer experience, and ML platform integrations.
Take end-to-end ownership of services — from design and deployment to monitoring, alerting, and iteration based on model and product performance.
Mentor teammates and champion engineering best practices in an ML-heavy environment.
Our expectations
Strong backend engineering experience using Python and/or Go, ideally in ML-adjacent or data-intensive systems.
Solid understanding of distributed systems, microservices, and API design in production environments.
Experience building and operating high-performance, low-latency services at scale (e.g. thousands of RPS, strict latency SLAs).
Hands-on experience with containerisation and orchestration (Docker, Kubernetes) and cloud platforms (AWS, GCP, or similar).
Experience integrating, deploying, or supporting machine learning models in production (e.g. inference services, feature pipelines, experimentation, or model monitoring).
Familiarity with ML system concerns such as model versioning, rollout strategies, A/B testing, and performance monitoring is a strong plus.
Strong understanding of observability and debugging in distributed, ML-powered systems.
Ability to collaborate in cross-functional teams, balancing model performance, engineering quality, and user impact.
What we offer
The opportunity to shape Wolt’s personalisation systems, serving millions of customers daily.
Be involved in rolling out new AI products for solving real customer problems with a measurable business impact.
Work in a cross-disciplinary environment with ML Engineers, Applied Scientists, Data Scientists, Designers and Product Leads who share your passion for building great customer-facing products.
A culture of ownership and excellence — you’ll take projects from conception to production and see the impact on users quickly at Woltwide.
Have a tangible and measured impact on Wolt’s business KPIs and Wolt's customers’ experience.