Oleguer Canal
Machine Learning Engineer at Apple
Barcelona, Catalonia, Spain
Summary
👤
Senior🎓
Top SchoolOleguer Canal is a machine learning engineer with 8 years of experience building production-grade AI systems, currently contributing to large-scale ML within Apple’s Services Team. He has a strong applied ML background from roles at Happy Scribe—where he led in-house training infrastructure and sequence-model experiments that cut AI costs by 54% and improved conversion and reviewer accuracy—and research stints at KTH, MIT and EA on robotics, perception and multi-task reinforcement learning. His work spans speech-to-text, diarization, confidence estimation, timestamping and agentic transcription improvement, combining experimentation (CTC, Transducer, Transformer, Diffusion) with rigorous A/B testing and real-time monitoring. Comfortable moving research into customer-facing products, he pairs a formal ML education from KTH with hands-on engineering across robotics and SaaS, and has a knack for squeezing operational AI costs without sacrificing user experience. An unusual strength is his cross-domain fluency: from tactile-driven robotic grasping to large-scale speech systems, he bridges perception, RL and production ML. Located in Barcelona, he brings both academic depth and measurable product impact to ML engineering challenges.
8 years of coding experience
7 years of employment as a software developer
BSc Final Thesis, Mathematics & Industrial Engineering, BSc Final Thesis, Mathematics & Industrial Engineering at Massachusetts Institute of TechnologyMaster's degree, Machine Learning, Master's degree, Machine Learning at KTH Royal Institute of TechnologyMathematics & Industrial Engineering, Mathematics & Industrial Engineering at CFIS-UPCUPC Universitat Politècnica de Catalunya
Catalan, Spanish, English, German
Stackoverflow
55reputation
3kreached
1answer
4questions
Github Skills (86)
transformers10
language-model10
python10
automatic-speech-recognition10
generative10
deep-learning10
chessboard10
transformer10
nlp10
jax10
seq2seq10
tensorflow10
natural-language-processing10
pytorch10
machine-learning10
Programming languages (8)
Github contributions (5)
OleguerCanal/RL-algorithms
Nov 2019 - Mar 2020
KTH Reinforcement Learning (EL2805) 2019 coding assignments
Contributions:118 commits, 1 PR, 73 pushes in 4 months
reinforcement-learningreinforcementkthdeep-reinforcement-learning
OleguerCanal/camera-calibrator
Sep 2019 - Jun 2022
Code to automate multiple-camera calibration (2D or 3D) with oriented chessboard using AprilTag. Either for static or eye-in-hand applications.
Contributions:43 commits, 1 PR, 31 pushes in 2 years 8 months
pythoncamerachessboardapriltagcalibration
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.