Sr. Machine Learning (Data Scientist)

The Impact You Will Make:

- Help the business gain insights from recommendations in search and discovery with regard to short and long term metrics

- Drive orders and diner returns via enticing and relevant recommendations for searches

- Bring state of the art advances in IR systems to our runtime environment. 

- Assess new algorithms and business policies

- Collaborate with Product and Engineering teams to understand new product ideas, assess risks and ensure that the necessary data is available

- Discover new and innovative ways to refine what we're doing and question existing assumptions.

- Relentlessly analyse and improve the performance of our business

Responsibilities:

- Develop and iterate on models for search ranking and personalised recommendations, using established deep-learning and IR techniques.

- Define clear performance metrics and contribute to automated evaluations, dashboards, and alerting that keep models healthy in production.

- Optimize training and inference jobs for cost and latency, making judicious use of GPUs and other accelerators.

- Follow and promote best practices in model versioning, testing, monitoring, and ethical AI.

- Build and maintain feature pipelines in PySpark/Hive/Python, ensuring data quality and reproducibility.

- Run controlled experiments (A/B tests), interpret results, and recommend data-driven next steps to product and engineering partners.

- Prototype promising research ideas e.g., transfer learning or LLM-based features and help transition successful prototypes into stable services.

- Stay current with the field, summarising relevant papers or tools and suggesting incremental improvements to the teams toolkit.

- Collaborate closely with product managers and engineers to scope work, surface trade-offs, and deliver diner-facing improvements on schedule.

- Share knowledge through code reviews, informal mentoring, and concise technical documentation accessible to mixed audiences.

Requirements:

- MS/PhD in quantitative discipline (Computer Science, Math, Physics, Engineering, Statistics or other technical field etc) or equivalent experience

- 4+ years experience with data analytics, machine learning, or related field

- 2+ years experience in applied predictive modeling with TensorFlow

- 2+ years experience in information retrieval or recommendation systems

- Experience with language models, especially on imperfect grammars

- Experience with Large Language Models (LLMs), including fine-tuning and deploying transformer-based architectures in real-world applications

- Experience tuning runtime models using GPUs

- Experience in data engineering and feature preparation in pyspark, hive, and the python data stack.

- Comfort communicating performance metrics, model details, and features specifications to technical and non-technical audiences

- Ability to keep up with the latest publications and synthesise research into working models

- Deep interest in self-motivated continuous learning

Additional information/Benefits:

- Work with some of the most dynamic US tech companies, building and iterating on new features and platforms.

- Long-term projects with real technical challenges.

- Fully remote work with flexible hours.

- Option to work from our office in Cluj-Napoca, Romania, if desired.

- Collaboration flexibility: We work with CIM/PFA/SRL contracts.

- 30 paid days off per year.

- We provide equipment as needed (laptop, desktop, etc.).

- Continuous learning: We sponsor career-improving courses, seminars, and certifications.

- Opportunity for annual business visits to the US, depending on project needs.

Get picky and choose a career that matches your mindset and lifestyle. Team up with a company that encourages you to do more and gives you the flexibility you need!