Over Tom
I am a versatile Data Scientist and Pre-Sales Engineer with a proven track record of building end-to-end data solutions in high-velocity IoT environments. At Suivo, I acted as a bridge between complex infrastructure and actionable business value, serving as part of a specialized two-person Data & Infra team.
What I bring to your project:
Technical Architecture: Expert in building scalable data pipelines using Apache Beam and GCP. I don't just build models; I deploy them using Kubernetes, Jenkins, and CI/CD best practices.
Business Translation: I excel at requirement analysis—taking vague business questions and translating them into technical use cases that deliver measurable product value.
Pre-Sales & Strategy: With a background in pre-sales, I help stakeholders understand the 'why' behind the data, delivering external dashboards and predictions that drive client engagement.
Whether you need a robust data infrastructure on GCP/Azure or a machine learning specialist who can also speak to your customers, I provide the full-stack expertise to move from data to insights.
Nederlands
Tweetalig / moedertaal
Engels
Vloeiend
Frans
Beperkte professionele capaciteit
Kan op locatie werken
Schaarbeek (tot 50km)
Werkervaring
- SuivoData Scientist & Pre-Sales EngineerTRANSPORT & LOGISTIEKnovember 2024 - Vandaag (1 jaar en 7 maanden)2650 Edegem, BelgiumAs a core member of a two-person Data & Infrastructure team, I was responsible for the end-to-end delivery of data products for an industry-leading IoT and telematics platform. My role bridged the gap between deep technical implementation and client-facing business strategy.Key Responsibilities & Impact:Data Product Development: Engineered and deployed scalable data-based insights and predictive models that directly enhanced the Suivo product ecosystem.Full-Stack Pipeline Management: Designed and maintained robust ETL pipelines using Apache Beam and GCP, ensuring high-availability data for external client dashboarding.Infrastructure & DevOps: Managed the deployment lifecycle using Kubernetes, Jenkins, and CI/CD pipelines to ensure seamless integration of data services.Strategic Pre-Sales: Partnered with the sales team to perform requirements analysis and translate complex client needs into technical use cases and implementation roadmaps.IoT Analytics: Leveraged Tensorflow and advanced SQL (via DataGrip) to turn raw asset-tracking data into actionable business intelligence for fleet and resource management.
- Flanders MakeResearch StudentONDERZOEKSCENTRAjanuari 2023 - januari 2024 (1 jaar)Leuven, BelgiëDeveloped a cutting-edge, real-time defect detection system for Laser Powder Bed Fusion (LPBF) using advanced 3D Convolutional Neural Networks (3DCNNs). The research focused on predicting material mass density directly from coaxial camera frames to enable in-process quality control.Key Achievements & Methodologies:Deep Learning Architecture: Designed and benchmarked robust 3DCNN regression models using PyTorch, specifically comparing ResNet and SlowFast architectures.Model Performance: Demonstrated that the SlowFast dual-pathway model significantly outperformed standard architectures by capturing both high-temporal-resolution features and spatial details of the melt pool.Data Pipeline & Preprocessing: Engineered a complex data preparation workflow using OpenCV and Scikit-image, including Total Variation (TV) denoising, outlier detection, and the alignment of high-speed camera frames (20k fps) with post-process X-ray Computed Tomography (X-CT) slices.High-Performance Computing: Leveraged the VSC (Flemish Supercomputer Center) to train models on large-scale volumetric datasets (HDF5 format), achieving rapid RMSE convergence.Statistical Validation: Performed rigorous correlation analysis between laser energy density (power/speed) and voxel intensity to identify defect-prone printing parameters.
Aanbevelingen
Wees de eerste die Tom aanbeveelt
Help deze freelancer om te schitteren door te vertellen hoe het is om met hem of haar te werken.
Deze freelancerprofielen matchen ook met zoekopdracht.
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Opleidingen
- M. Sc.Catholic University Leuven2024M. Sc.