Product ML Engineer

Hi there!

We're SweedPos, a product-driven startup building an all-in-one cannabis retail platform. We’re on the lookout for a Senior ML Engineer to join us remotely and help us build recommendation and personalization systems across our eCommerce ecosystem.

About Us

At Sweed, we’re reimagining how cannabis retailers operate. Our enterprise-grade platform combines POS, eCommerce, Marketing, Analytics and Inventory Management into a single, seamless solution - eliminating the need for multiple third-party tools.

We believe in simplicity, efficiency, and innovation. That’s why we build for scalability and performance, making life easier for cannabis retailers while driving real business growth.

Why We’re Doing This

At Sweed, we believe in the medicinal potential of cannabis. It has been shown to help with chronic pain, anxiety, depression, and many other conditions. Despite the lingering stigma, we see cannabis as a powerful tool for improving lives.

The industry is evolving rapidly, and we’re here to drive that transformation - making cannabis retail more efficient, accessible, and customer-friendly.

Where We Are Now

We’ve been on the market for 8 years, continuously growing and refining our product.

Our focus is on earning customer trust, which means constantly improving our delivery processes and rolling out new features. At the same time, we navigate the complex legal landscape of the cannabis industry, ensuring our platform remains compliant and future-proof.

Team Structure

Our total team size is over 200 people:

The development team is distributed globally and organized into cross-functional product teams. These teams typically consist of 8-12 members, including front-end and back-end developers, QA specialists, and analysts.

Each team is led by a Team Lead and a Product Owner, ensuring effective collaboration and clear direction.

Meanwhile, our CEO, account managers, and customer success team are based in the USA, working closely with us to align product development with business and user needs.

About the Role

You’ll work primarily within our eCommerce domain, helping us build the next generation of recommendation and personalization capabilities.

We already have recommendation functionality running in production, including product recommendations and customer-facing eCommerce experiences. At the same time, we’re still at an early stage when it comes to true personalization.

Our long-term goal is to build a shopping experience that adapts to each customer - from which products and content they see to how different parts of the journey are ranked, assembled, and presented.

This is a particularly interesting stage to join because many foundational decisions are still ahead of us. You’ll have the opportunity to influence the architecture, tooling, experimentation approach, data requirements, and overall direction of our recommendation systems.

Unlike in mature recommendation teams, where most of the infrastructure is already established and engineers focus on incremental optimization, here you’ll have the opportunity to build a significant part of the system from the ground up.

What You’ll Do

• Build and improve production recommendation and ranking systems.

• Develop personalization models across different parts of the eCommerce customer journey.

• Work on candidate generation, retrieval, ranking, and re-ranking approaches.

• Design personalized product feeds, carousels, content ordering, and next-best-action experiences.

• Contribute to customer behavior, demand, and product-level forecasting use cases.

• Connect recommendation systems with search and conversational shopping experiences.

• Define and track offline ML metrics and online product metrics.

• Design and run experiments and A/B tests to validate product hypotheses.

• Build scalable inference services and ML APIs.

• Improve feature pipelines, training workflows, monitoring, and internal ML tooling.

• Work closely with Data Platform and backend teams to ensure the right behavioral and transactional data is available.

• Participate in architectural discussions and technical decision-making.

• Help Product teams translate business problems into measurable ML problems.

What You’ll Be Working On

Some of the initiatives we’re currently exploring include:

• evolving our existing recommendation engine;

• building deeper customer-level personalization;

• personalized product ranking and content selection;

• dynamic homepage and carousel composition;

• next-best-action models;

• recommendation-powered conversational shopping experiences;

• AI-powered product search;

• customer behavior and demand forecasting;

• improving the data and feature pipelines behind ML systems;

• building better experimentation and evaluation workflows.

The exact roadmap will evolve, and we expect you to actively contribute to shaping it.

What We’re Looking For

• 5+ years of production ML / Machine Learning Engineering experience.

• Strong commercial experience with recommendation systems.

• Strong Python and SQL skills.

• Experience working with ranking, retrieval, candidate generation, collaborative filtering, embeddings, learning-to-rank, or similar recommendation approaches.

• Experience building and maintaining production ML systems.

• Experience working with offline ML metrics and online product/business metrics.

• Experience with A/B testing and experimentation.

• Strong understanding of the full ML lifecycle: experimentation, deployment, monitoring, and iteration.

• Experience building APIs or production inference services.

• Good understanding of data pipelines and working with behavioral or transactional data.

• Familiarity with MLOps, CI/CD, observability, and production reliability.

• Strong software engineering fundamentals.

• Experience making technical decisions and taking ownership of solutions.

• Ability to work independently in ambiguous environments.

• Strong communication skills and a collaborative mindset.

• Ability to work directly with Product teams, clarify requirements, challenge assumptions, and help shape the right solution.

Nice to Have

• Experience with forecasting or time-series models.

• Experience with demand forecasting or customer behavior prediction.

• Experience with eCommerce, marketplaces, advertising, food delivery, or other recommendation-heavy products.

• Experience with personalization systems.

• Experience with search or information retrieval.

• Experience with data engineering or data modeling.

• Experience building feature pipelines, feature stores, or metric layers.

• Experience developing internal ML tooling or ML platforms.

• Experience with model serving or inference optimization.

• Experience building ML systems from an early stage rather than only maintaining an established stack.

What Matters Beyond Technology

Ownership

We’re looking for engineers who take responsibility for outcomes rather than simply implementing predefined tasks.

That means understanding the problem, identifying dependencies, driving the technical solution, getting it into production, and following the results afterwards.

Product Thinking

We care about building ML systems that improve real product and business metrics - not simply optimizing offline model quality.

You should be comfortable asking what problem we’re actually solving, how success will be measured, and whether ML is the right solution in the first place.

Communication

This role requires close collaboration with Product, Engineering, Analytics, and Data Platform teams.

Our product organization is still developing deeper ML expertise, so we’re looking for someone who can ask the right questions, explain constraints clearly, challenge requirements constructively, and help teams turn broad ideas into concrete ML problems.

Curiosity

Recommendation systems, personalization, and modern ML evolve quickly. We value engineers who actively explore better approaches, experiment, and continuously expand their technical expertise.

Pragmatism

We value engineers who know how to balance product quality, engineering complexity, latency, maintainability, and business value.

Adaptability

Our ML infrastructure and product roadmap are still evolving. We’re looking for someone who is comfortable building in an environment where not everything is already defined and where part of the job is improving the systems and processes around you.

ML-Driven Product Development

Machine learning is becoming an increasingly important part of how we build our product.

We already have recommendation systems running in production, a growing Data Platform, and foundational ML infrastructure. At the same time, there is still significant room to improve how we approach personalization, experimentation, feature pipelines, model lifecycle management, and production monitoring.

We’re looking for someone who wants not only to build models, but also to help shape the technical foundation that makes ML development faster, more measurable, and easier to scale across the company.

Working Style

• Close collaboration with Product, Engineering, Data Platform, and Analytics teams.

• High level of ownership over ML initiatives.

• Product requirements are translated into ML system designs before implementation.

• Regular technical discussions and design reviews.

• Experimentation and A/B testing are an important part of product development.

• You’ll work across different eCommerce teams depending on the problem rather than being limited to one narrow product squad.

What We Offer

• Salary in USD (B2B contract with the US company)

• 100% remote - We’re a remote-first company, no offices needed!

• Flexible working hours - Core team time: 10:00-16:00 CET (flexible per team)

• 20 paid vacation days + 12 holidays per year

• 3 sick leave days

• Medical insurance after probation

• Equipment reimbursement (laptops, monitors, etc.)

Hiring Process

Recruiter Call (45 minutes)

Introduction, role overview, experience discussion, and English check.

Experience Deep Dive (60 minutes)

A detailed discussion of one of your most relevant production ML projects, ideally related to recommendation systems or forecasting. We’ll explore the business context, architecture, constraints, technical decisions, trade-offs, metrics, experimentation, and your personal contribution.

ML System Design (60 minutes)

A practical architecture discussion based on a problem similar to the ones you could work on at Sweed, most likely related to recommendations, personalization, or forecasting.

Final Interview (60 minutes)

A conversation with the ML and eCommerce leadership focused on product thinking, ownership, cross-functional collaboration, communication, and overall fit for the role.