About自己紹介
I build deep-learning systems for signal processing at scale — pulling robust structure out of noisy, high-volume data, and shipping it so it holds up in production.
I build systems for the hard cases — faint signals, large data, and decisions where being wrong is expensive.
That’s how I see the research engineer’s job: turn a promising model into something that runs reliably outside the notebook. My background is unusually wide for it — a PhD in computational neuroscience from King’s College London (deep learning and explainable AI for brain connectivity), on top of eight-plus years in industry spanning Linux-kernel and embedded systems, ML platforms, and a co-founded health-tech startup.
Today I’m a Research Software Engineer at the University of Glasgow, enhancing a clinically deployed ECG program that interprets 20M+ recordings a year — building deep-learning models for arrhythmia detection, noise classification, and signal-quality, and bringing modern ML rigour to a fifty-year-old, safety-critical codebase.
The methods I reach for — detection in noise, time-series modelling, denoising, anomaly detection — are the family astronomy uses to pull faint sources and transients out of overwhelming backgrounds. That cross-pollination, toward larger data and fainter signals, is where I’m heading next.
Toolbox道具
The languages, frameworks, and systems I reach for.
Languages
ML / DL
Signal & data
Systems & scale
Domains
Experience経歴
Sixteen years across academia and industry — research, engineering, and shipping.
Research Software Engineer
University of Glasgow · Glasgow, UK
- Enhancing the Glasgow ECG analysis program — a clinically deployed algorithm used to interpret 20M+ electrocardiograms a year — with deep-learning models for arrhythmia detection, noise classification, and signal-quality assessment.
- Bringing modern ML practice (rigorous evaluation, testing, reproducibility) to a fifty-year-old, safety-critical codebase and hardening its pipelines for dependable clinical deployment.
Co-founder & CTO
Tycho MedLink · London, UK
- Co-founded a digital-therapeutics startup and owned all technology for a VR treatment for Seasonal Affective Disorder, from prototype to clinical pilot.
- Raised £100k across two UKRI rounds (UCL and Cambridge alumni accelerators); ran early trials with UCL Hospitals that demonstrated efficacy.
- Built the VR product in Unity for Meta hardware with instrumented user metrics.
PhD Researcher, Machine Learning & Neuroimaging
King's College London · London, UK
- Developed deep-learning methods — graph neural networks with explainable-AI attribution (SmoothGrad, Grad-CAM) — to predict neurodevelopmental outcomes from neonatal brain connectivity.
- Worked in the CoDe Neuro lab alongside clinicians at the Centre for the Developing Brain; results published and presented at OHBM.
Senior Research Engineer
Prepaire · Dubai, UAE (Remote)
- Led development of AI models, including custom LLMs, to automate genomic data-analysis pipelines — cutting processing time by ~40%.
- Shipped models into a high-performance production environment with scalability as a first-class concern.
Teaching Assistant, Deep Learning
Neuromatch · Remote
- Taught deep learning (PyTorch, neuroimaging tooling) to an international cohort; ran daily labs and project work.
Research Software Engineer
Google Summer of Code · London, UK
- Built an infant eye-tracking API prototype, mentored by McGill University’s ophthalmology group.
Technical Editor, Computer Vision
RSIP Vision · Remote
- Reviewed and distilled state-of-the-art computer-vision and medical-imaging research for a specialist readership (Computer Vision News).
Senior Machine Learning Engineer
Saddington Baynes · London, UK
- Built AI image-processing automation (TensorFlow) that cut manual work ~50%, with GPU-accelerated Docker and optimised CI/CD for model deployment.
Software Engineer, Linux Kernel
Microsoft · UK
- Optimised cloud hypervisor systems at the kernel level (C) for performance and stability; contributed to virtualization R&D.
Systems Software Engineer
Kano Computing · London, UK
- Built and maintained a Linux-based OS (system services, Qt/C++ and GTK); cut image build time from 4 hours to 30 minutes and added CI/CD.
Research Software Engineer, Serious Games
University of Athens · Athens, Greece
- Built an accessible “serious game” for children with mild disabilities (Epinoisi R&D) in PyGame/WebGL with a C++ game AI.
Embedded Systems Engineer
INTRACOM Defense Electronics · Athens, Greece
- Embedded R&D (FPGA, microcontrollers) for a military comms system under NATO clearance; built an automated test framework validated to NATO/MIL-STD.
Publications論文
Peer-reviewed papers, conference work, and abstracts.
μ-Opioid Modulation of Sensorimotor Functional Connectivity in Autism: Insights from a Pharmacological Neuroimaging Investigation using Tianeptine
Dimitrov, M., Wong, N.M.L., Leaman, S., França, L.G.S., Valasakis, I., He, J., Lythgoe, D.J., Findon, J.L., Wichers, R.H., Stoencheva, V., Robertson, D.M., Blainey, S., Ivin, G., Holiga, Š., Tricklebank, M.D., Batalle, D., Murphy, D.G.M., McAlonan, G.M., Daly, E.
Biological Psychiatry Global Open Science
Explainable Deep Learning for Subtyping: A SmoothGrad Approach
Valasakis, I., Batalle, D., Deprez, M.
OHBM 2024
Predicting Neurodevelopmental Phenotypes from Neonatal Brain Connectivity using Graph Neural Networks
Valasakis, I., Batalle, D., Deprez, M., McAlonan, G.
OHBM 2023
Deep learning-based reconstruction for 3D coronary MR angiography with a 3D variational neural network (3D-VNN)
Qi, H., Hammernik, K., Lima da Cruz, G., Valasakis, I., Rueckert, D., Prieto, C., Botnar, R.
ISMRM 2021
Development of a Processing Toolset for Ion Mobility Mass Spectrometry
Valasakis, I.
MSc Thesis — Birkbeck, University of London
Contact連絡
Open to interesting problems in signal, scale, and learning. The fastest way to reach me is email.
Open to
- Research & engineering roles in signal / ML at scale
- Collaborations on time-series and detection problems
- Speaking, peer review, and technical writing