CV

Click to access cv.pdf

Profile

With a background in humanities and computer science, I bridge these domains to ensure technology moves forward responsibly. I stay critical yet optimistic about what AI can do, always aiming for positive outcomes that resonate beyond the lab. I enjoy communication; Iā€™m comfortable speaking to diverse audiences and holding conversations that connect ideas across fields.

Experience

Assistant Professor | ILLC, University of Amsterdam ā€” Feb 2025 ā€“ Present
AI for OpenGov ICAI Lab Manager at the Institute for Logic, Language and Computation. The OpenGov lab is set up in partnership with the Rijksorganisatie voor Informatiehuishouding (RvIHH), focusing on applied IR and NLP for government transparency.

Lead Data Scientist | Randstad N.V., Diemen, NL ā€” Aug 2023 ā€“ Dec 2024
Responsible for responsible AI across technology, legal, data protection, and compliance. Led audits, bias mitigation, and participated in EU AI Act study groups.

Lead Data Scientist & Chapter Lead | Randstad Groep Nederland, Diemen, NL ā€” Mar 2020 ā€“ Jul 2023
Led the data science chapter (12+ scientists), focusing on recommender systems, NLP, forecasting, and fairness projects.

Lead Data Scientist | FD Mediagroep, Amsterdam, NL ā€” Apr 2018 ā€“ Dec 2019
Led personalization projects like BNR SMART Radio and FD SMART Journalism. Delivered content-based news recommenders and CMS automation.

Data Scientist | Company.info, Amsterdam, NL ā€” Oct 2016 ā€“ Sep 2018
Worked on entity linking, sentiment classification, and sector classification of financial/company data.

Science Editor | NTR, Hilversum, NL ā€” 2008 ā€“ 2011
Worked as science editor for radio and online portal Wetenschap24 after completing BA.

Internships and Visits

Research Intern | Microsoft Research, Redmond, USA ā€” Jun 2015 ā€“ Sep 2015
Published award-winning paper on Cortana logs, filed patent.

Visiting Researcher | University of Maryland, College Park, USA ā€” Feb 2014 ā€“ Jan 2014
Research on e-discovery and publication at SIGIR 2014.

Education

PhD Information Retrieval | University of Amsterdam ā€” 2012 ā€“ 2017
Thesis: Entities of Interest ā€” Discovery in Digital Traces
Promotor: Prof. dr. Maarten de Rijke

MSc Media Technology | Universiteit Leiden ā€” 2009 ā€“ 2012
Thesis: Automatic Annotation of Cyttron Entries using the NCIthesaurus

BA Media Studies | University of Amsterdam ā€” 2004 ā€“ 2008
Minor: American Studies

Professional Activities

  • Committee Member | Commissie Persoonsgegevens Amsterdam (CPA)
  • Advisory Board Member | AIQUITY
  • Board Secretary | SETUP, Utrecht
  • Co-organizer | RecSys in HR Workshop (2021ā€“2024)
  • Committee Member | Veld Adviesraad Master Applied AI (HvA)
  • Principal Investigator & WP Leader | FINDHR (Horizon Europe)
  • Co-chair | DDMA AI Committee
  • Local Outreach Chair | ACM RecSys 2021
  • Committee Member | HU School of Journalism
  • Co-organizer | DIR 2019
  • Communications Officer | ILPS, UvA
  • PhD Council Chair | Informatics Institute, UvA
  • Publicity Chair | ECIR 2014

Academic Activities

  • Conference PC: RecSys Industry (2024), UMAP (2021ā€“2023), SIGIR (2015ā€“2022), CIKM (2015, 2017)
  • Workshop PC: EWAF ’24, AI for HR & PES (2023ā€“2024), PodRecs@RecSys 2020, NewsIR@ECIR 2016
  • Journal Editor: Frontiers in Big Data ā€” Recommender Systems for Human Resources
  • Misc: TalentCLEF Scientific Committee member

Teaching

Invited Lectures (Selection)

  • ACM Summer School RecSys ā€” Copenhagen, 2023; Gothenburg, 2019
  • UvA in DeLaMar Business Seminar ā€” Amsterdam, 2022
  • Universiteit Twente ā€” Guest lecture, 2021
  • Universiteit Leiden ā€” AI for lawyers, 2020
  • VOGIN-IP Lezing ā€” Amsterdam, 2018
  • Multiple panels and keynotes (full list available in original CV)

Student Supervision (Selection)

Supervised MSc thesis work across VU, UvA, Leiden, Radboud, and FD Mediagroep with multiple publications.

University Courses

  • Web Search (MSc)
  • Complex Crime Scenes (MSc Forensic Science)
  • Social Network Analysis (BSc)

Selected Publications

General Public

  • Forget the Trolley Problem; Pragmatic and Fair AI in the Real World, TowardsDataScience, 2021
  • Wij zijn racisten, daarom Google ook, NRC Handelsblad, 2016

Peer-Reviewed (Selection)

  • Fabris et al. Fairness and bias in algorithmic hiring: a multidisciplinary survey, ACM TOIS, 2025
  • Lavi et al. conSultantBERT: fine-tuned siamese sentence-bert for matching jobs and job seekers, RecSys HR ā€™21
  • Lu et al. Beyond optimizing for clicks: incorporating editorial values in news recommendation, UMAP 2020
  • Berlage et al. Improving automated segmentation of radio shows with audio embeddings, ICASSP 2020
  • Graus et al., The birth of collective memories: analyzing emerging entities in text streams, JASIST 2018
  • Graus et al. Analyzing and predicting task reminders, UMAP 2016
  • Graus et al. Dynamic collective entity representations for entity ranking, WSDM 2016

In the Press (Selection)

Interviews, podcasts, and media appearances include:

  • Filosofie in Actie Podcast (2024)
  • ING Sector Magazine (2024)
  • Shaping the Future Podcast (2023)
  • The Netherlands Institute for Human Rights (2023)
  • RecSperts Podcast (2022)
  • Reflex Magazine (2022)
  • European Science-Media Hub (2019)
  • Denktank (NTR, 2017)
  • And many more

Selected Invited Talks

Includes keynotes, panel talks, and invited lectures at:

  • UWV IV-Conference (2024)
  • NLP4HR Workshop at EACL (2024)
  • CPDP (2023, 2020)
  • Reshaping Work Conference (2022)
  • FEAST Workshop (2021)
  • Dataiku Webinar (2021)
  • ICT.Open (2021)
  • Anti-Discrimination Hackathon (2020)
  • Academisch-Cultureel Centrum SPUI25 (2019)
  • VOGIN-IP Lezing (2018)
  • De Balie (2017)
  • Koninklijke Marechaussee Intelligence Dag (2016)

Patents

  • System for interpreting and managing imprecise temporal expressions, US10719757B2, Microsoft (2020)

Awards

  • Dutch Interactive Awards (2019)
  • Annual Masters of Media Awards (2019)
  • Marconi Online Award (2019)
  • UMAP Best Student Paper Award (2016)
  • ILPS MVP Award (2014)

Skills

Programming: Python, Bash, Clojure, C#, LaTeX, JavaScript, HTML, CSS
Libraries: scikit-learn, xgboost, numpy, pandas, spaCy, NLTK, D3
AWS: Lambda, ECS, ECR, SSM, Redshift, ElastiCache, SageMaker
Databases: MongoDB, Elasticsearch, SQL, Redis
Other: Adobe Creative Suite, Microsoft Office

Languages

  • Dutch (native)
  • English (fluent)
  • French (high proficiency)
  • German (basic)

Hobbies

Visiting museums, reading science fiction, craft beer, photography, graphic design, traveling, running, yoga.