Riskified вчера

Staff Data Scientist - Foundation Models

  • Tel Aviv
  • Гибрид
  • Опыт от 6 лет
LLMMachine LearningRisk ManagementDeep LearningFraud DetectionTransformerFoundation Models

Описание

Responsibilities

  • Lead the foundation model initiative: Own the research and roadmap for applying foundation models to our core problems, from proof of concept to real-time production.
  • Validate before you scale: Challenge assumptions, set success criteria tied to business metrics, and let evidence from early experiments steer the direction.
  • Build or adapt, whichever wins: Decide between training our own models and adapting existing ones, such as tabular foundation models, LLMs and pre-trained sequence models. Then develop the sequence, transformer, graph or deep tabular models that work on massive transaction and behavioural data.
  • Go deep on our domain and systems: Learn our fraud domain, data and production models, and find where learned representations add the most value.
  • Partner across functions: Work with Data Engineering, ML Platform, Core Software and Product on the data, training and serving infrastructure these models need.
  • Raise the bar: Bring the latest research into practical solutions, set standards for research rigour, and mentor data scientists across the department.

Requirements

  • Education: M.Sc. or Ph.D. in Computer Science, Statistics, Mathematics or a related quantitative field.
  • Experience: 6+ years of hands-on experience designing, training and deploying machine learning models in large-scale production environments.
  • Foundation model expertise: Hands-on experience building, fine-tuning or adapting foundation models or similar large-scale models, such as pre-trained transformers, self-supervised sequence models, tabular foundation models or LLMs. You have sound judgement on when to build and when to reuse.
  • Research judgement: A track record of turning open-ended research questions into well-designed experiments and evidence-based decisions.
  • Problem-first mindset: You start from the problem, not the technique, and you're comfortable challenging ideas, including your own, with data.
  • Curiosity and learning speed: You're eager to learn new technology as well as existing solutions, data and domain, and you ramp up quickly in unfamiliar territory.
  • Big data: Strong practical experience with large-scale distributed data processing (for example Spark or Databricks) and with training models on large datasets.
  • Technical influence: Proven technical leadership beyond your own team, including setting direction, aligning stakeholders and mentoring senior scientists.
  • Communication: You can explain complex research and trade-offs clearly to technical and non-technical audiences, including senior leadership.

Nice to have

  • Experience pre-training models on event, transaction or behavioural sequences (non-text data).
  • Experience with tabular foundation models, graph neural networks or embedding-based models at scale.
  • Experience in fraud detection, risk management, payments or fintech.
  • Publications, open-source work or talks in relevant areas.

We offer

  • Our Tel-Aviv team is currently working in a hybrid of remote and in-office work.
  • Equity for all employees, Keren Hishtalmut, pension
  • Private medical insurance, extra time off for parents and caregivers
  • Commuter and parking benefits
  • Team events, fully-stocked kitchen,lunch stipend, happy hours, yoga, pilates, functional training, basketball, soccer
  • Wide-ranging opportunities to volunteer and make an impact
  • Commitment to your professional development with global onboarding, skills-based courses, lunch & learns
  • Awesome Riskified gifts and swag!