Nicholas Santavas
Tech Lead & Manager, ML Engineer at eBay
Utrecht, Utrecht, Netherlands
Summary
👤
Senior🎓
Top SchoolNicholas Santavas is a tech lead and ML engineering manager based in Utrecht with eight years of experience building efficient AI systems across computer vision, NLP and large language model inference. He combines a PhD-level research focus on efficient neural networks and compression with hands-on MLOps expertise—optimizing models for production using quantization, Triton, TensorRT and vLLM to cut costs and boost throughput. At eBay and prior roles at Axelera and G42 he led model zoo development, scalable CI pipelines and multi-GPU distributed training, translating hardware-aware research into deployable solutions. He has a track record of shipping real-time CV and RAG-based NLP services on Kubernetes and edge AI chips, and his work often centers on squeezing maximum performance from constrained compute. Colleagues value him for bridging deep research insights with pragmatic engineering to deliver measurable production impact.
8 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD Candidate, Computer Vision, Efficient Neural Networks, Doctor of Philosophy - PhD Candidate, Computer Vision, Efficient Neural Networks at Democritus University of Thrace - (D.U.Th.)
Github Skills (44)
pytorch10
python10
apple-silicon10
machine-learning10
linux10
inference10
deep-learning10
tensorflow10
neural-network10
object-detection10
computer-vision10
yolov410
ml9
llm9
amd9
Programming languages (3)
Github contributions (5)
nsantavas/Attention-A-Lightweight-2D-Hand-Pose-Estimation-Approach
Sep 2020 - Aug 2021
Attention! A Lightweight 2D Hand Pose Estimation Approach paper code
Contributions:12 commits, 2 PRs, 11 pushes in 10 months
pose-estimation
nsantavas/mlx
Dec 2023 - Dec 2023
MLX: An array framework for Apple silicon
Contributions:16 pushes, 2 branches in 12 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.