Data Scientist

BGTS is a software and technology solutions company with over 1,800 professionals and 25+ years of experience. Through engineering expertise and industry insight, our international offices deliver tailored solutions, enabling clients worldwide to achieve their business goals with flexibility, speed, and impactful results.

We are looking for a highly skilled Data Scientist for our client to design and deploy end-to-end production pipelines for multimodal data synthesis.

What You’ll Be Doing:

• Deep expertise in VAE architecture design, training, and latent space manipulation for high-dimensional data synthesis and imputation.
• Proven experience in 3D CNNs, scene change detection (inter-frame histograms), and motion analysis (optical flow/peak detection).
• Ability to generate and fuse synthetic data across tabular, text, audio, and video formats using statistical modeling and Gaussian copulas.
• Advanced Python skills with a focus on modular design, production-level pipelines, and ffmpeg integration for audio/video handling.
• Familiarity with specialized techniques such as MDH/CDS/DSM exclusion and multimodal merger integration.

What We’re Looking For:

• Build standalone, testable modules for video metadata extraction, critical frame selection, and automated scene analysis.
• Lead the design of VAE-based systems for complex data imputation and synthesis.
• Execute a three-phase delivery model: 1) Extraction & Architecture, 2) Synthesis & Imputation, and 3) Cross-component optimization.
• Implement rigorous integration testing and quality metrics to ensure the fidelity of synthetic outputs.