Vladislav Li
Email: couper64@gmail.com | Location: London, UK
Profile
Software Engineer with a PhD in Artificial Intelligence and and extensive hands-on experience designing, deploying, and maintaining ML systems in production. Specialises in containerised infrastructure, distributed backend services, and GPU-based inference pipelines. Comfortable working across the full stack such as from bare-metal server setup and Linux administration through to cloud deployment and ML model integration. Brings both research depth and engineering rigour to building reliable, scalable AI systems.
Skills
MLOps & Infrastructure
- Docker and Docker Compose — containerised ML service design, multi-service orchestration
- CI/CD — GitHub Actions, automated build, test, and deployment pipelines
- Kubernetes — workload deployment and basic cluster orchestration
- ML model serving — inference pipeline design, GPU workload management, throughput optimisation
Backend Engineering
- FastAPI, Celery, Redis — distributed APIs, async task queues, message brokering
- REST API design and microservices architecture
- Linux systems administration — Ubuntu, Arch, Fedora, Void (scripting, service management, performance tuning)
- Networking — switches, structured cabling, IP configuration, system integration
Cloud & Infrastructure
- AWS EC2 — instance provisioning, service deployment, remote access configuration
- Azure AI Services — integration into backend processing and production ML workflows
- On-premise GPU server setup and maintenance
Programming
- Python — primary language for backend systems, ML tooling, and automation
- C / C++ — performance-critical and systems-level programming
- C# — application development (Unity, XR platforms)
- SQL — schema design, normalisation, query optimisation
- Lua — scripting and rapid prototyping
Experience
Research Engineer — AI Systems & MLOps
Kingston University, London | 2021 – Present
- Designed and deployed containerised ML inference systems using Docker on Linux servers, enabling reproducible, portable model serving across development and production environments
- Built distributed processing pipelines using FastAPI, Celery, and Redis to handle concurrent ML inference requests with reliable async task queuing
- Optimised GPU-based inference to meet real-time performance requirements in industrial simulation contexts
- Integrated ML model backends with VR/XR platforms (Unity, HoloLens) for EU-funded Industry 4.0 research projects
- Delivered production-grade backend services for AI workloads with focus on reliability, maintainability, and observability
- Configured and maintained on-premise Linux servers and GPU workstations supporting research infrastructure
Projects
Distributed ML Inference Platform
- Designed a horizontally scalable inference API using FastAPI with Celery worker pools and Redis as the message broker
- Containerised all services using Docker for consistent, reproducible deployment across environments
- Architected for concurrent workload distribution, separating compute-heavy GPU tasks from lightweight API routing
Cloud AI Deployment (AWS / Azure)
- Deployed ML inference endpoints on AWS EC2 with automated startup scripts and access control configuration
- Integrated Azure AI Services into production backend workflows for real-time AI-assisted processing
Industrial XR + AI Integration (EU-funded)
- Developed Unity-based XR applications that consume ML model outputs for industrial operator training simulations
- Coordinated ML backend services and XR frontend integration across a distributed research team
Education
PhD in Artificial Intelligence — Kingston University | 2021 – 2024
MSc Games Development (Programming) — Kingston University | 2019 – 2020
BSc (Hons) Computer Science (Games Programming) — Kingston University | 2015 – 2019
Publications
Research in computer vision and efficient AI systems. Full list available on request.
Additional
- VR/AR development: Unity, Unreal Engine, Microsoft HoloLens
- Robotics: Unitree platform, Python-based motion control and scripting
- Hardware: server and workstation build and configuration, GPU setup, structured cabling and network switches