Evgeny Krivosheev

Sr. AI Engineer and Tech Lead

Smiley face Hello! I am a Senior AI Engineer and Tech Lead at Jumio Corporation, where I’ve been driving innovation since October 2021. I lead Document Classification Team, focusing on ID verification for top clients like Airbnb, Uber, and TikTok. My work involves designing and productionalizing multimodal solutions with text and vision transformers, defining the AI roadmap, mentoring engineers, and coordinating cross-team efforts.

I was a Post-doctoral researcher in Multimedia Group at the University of Trento where my work spans over Graph Neural Networks for Computer Vision, Domain Adaptation, and Self-supervised Learning, in particular, when little or no supervision is available. I hold a PhD (Cum laude) in Computer Science from the University of Trento in 2020, where I worked on natural language, cost-aware active learning, crowdsourcing and hybrid crowd-machine learning algorithms for low-risk classification decisions.

In my work, I use a variety of Machine Learning and Deep Learning approaches, such as NLP, Transformers, LLMs, CNN, and Graph Neural Networks. For obtaining high-quality training data from (possibly) noisy sources, I implement state-of-the-art crowdsourcing and data fusion algorithms.

R&D Interests:

Document Retrieval Natural Language Processing Computer Vision
Graph Neural Nets LLM, Multimodal LLM, RAG Unsupervised Learning

Work Experience

Oct 2021 - Present Sr AI Engineer at Jumio Corporation, Italy / Austria
Research and Development for Bank Document and ID Verification from Photos
June 2020 - Oct 2021 Post-doctoral Researcher at Multimedia Group Unitn, Italy
Research in Graph Neural Networks for Computer Vision and Unsupervised Learning
May 2019 - Nov 2019 Deep Learning Intern at IBM Research, Zurich
Graph Neural Networks for record linkage and data modelling, Demo video.
June 2018 - Aug 2018 Machine Learning Intern at IBM Benelux, Amsterdam
Active learning and adaptive text classification algorithms.
Oct 2017 - Dec 2017 Deep Learning Intern at Pi School, Rome
Ransomware detection through analysis of user logs and RNN models, Demo video.
Jan 2016 – May 2016 Data Fusion intern at Purdue University, USA
Data fusion from noisy sources of information for object lifespan and ground truth inference.
Feb 2015 - Sep 2015 Python Software Engineer at iTechArt Group, Belarus
Dvelopment endpoints for RESTful web services.
Aug 2014 - Feb 2015 Embedded Software Engineer at Promwad Electronics, Belarus
Embedded software for one board Linux computers and microcontrollers.

Education

Nov 2016 - May 2020 PhD (Cum laude) in Computer Science, Univesity of Trento, Italy (advisor prof. Fabio Casati)
Sep 2011 - Jun 2016 Master in Aerospace Information Systems, Belarusian State University, Belarus

Activities

  • 01.2024 - Leading Document Classification Team at Jumio for supporting ID verification for customers such as Airbnb, UBER, TikTok, etc.
  • 12.2022 - By the end of 2022, I enabled Data Extraction from PII document scans and photos for French, German, Italian, Polish, and Dutch languages.
  • 10.2022 - Productionalized s Document-type Reclassification model resulting in the reduction of high-severity errors for customers and improving the overall document extraction process.
  • 07.2022 - accepted ECCV 2022 paper about Online Adaptation for Self-driving cars: "GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation"
  • 10.2021 - started new position as ML/AI Engineer at Jumio Corporation"
  • 10.2021 - reviewer at Big Data 2021 : IEEE International Conference on Big Data "
  • 07.2021 - accepted ECML PKDD paper: "Graph Neural Networks for Data Integration"
  • 06.2021 - accepted IEEE ICWS paper: "Crowd-Powered Hybrid Classification Services: Calibration is all you need"
  • 05.2021 - accepted a journal paper: "A review and experimental analysis of active learning over crowdsourced data" (Artificial Intelligence Review)
  • 02.2021 - accepted CVPR2021 paper: "Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation"
  • 11.2020 - two papers accepted for NeurIPS Workshops: i) Crowd Science and ii) Human in the Loop in Dialogue Systems
  • 10.2020 - program committe at NeurIPS Workshop 2020
  • 10.2020 - accepted a Demo paper for Conference on Artificial Intelligence (AAAI 2021)
  • 07.2020 - reviewer at Journal of Web Engineering
  • 06.2020 - accepted a full paper for Very Large Databases (VLDB 2020), video.
  • 06.2020 - gave a talk at PiSchool about Graph Neural Networks for Data Integration
  • 06.2020 - started a Post-Doc in Computer Vision at MHUG Group, University of Trento
  • 05.2020 - awarded PhD with Cum Laude from the University of Trento, Italy
  • 05.2019 - started research internship at IBM Research Zurich
  • 11.2018 - attending the ACM CSCW 2018 conference, New York, US
  • 06.2018 - started research internship at IBM Center for Advanced Studies Benelux, Amsterdam
  • 05.2018 - attended the TheWebCon (WWW-2018)
  • 12.2017 - passed the Ph.D. Qualifying Exam
  • 10.2017 - attended the HCOMP-2017 conference, participated in CrowdCamp
  • 10.2017 - won a grant and worked on a cyber-security deep learning project focused on Ransomware detection at Pi School
  • 11.2016 - started a PhD at the University of Trento, Italy