Vladislav Li
Profile
MLOps and Systems Engineer with a PhD in Artificial Intelligence, specialising in deploying and scaling machine learning systems in production environments. Experienced in building distributed backend services, containerised applications, and real-time inference pipelines. Strong background in Linux systems, Docker-based infrastructure, and GPU-enabled workloads across cloud and on-premise environments.
Key Skills
MLOps & DevOps - Docker, containerised deployments, distributed systems - CI/CD (GitHub Actions), automated workflows - Kubernetes (basic deployment and orchestration) - ML model deployment and inference pipelines
Backend & Systems - FastAPI, Celery, Redis (asynchronous and distributed processing) - REST APIs, microservices architecture - Linux (Ubuntu, Arch, Fedora, Void) - GPU workloads and performance optimisation
Cloud & Infrastructure - AWS (EC2 deployment, service configuration) - Azure (AI services integration) - Networking fundamentals (switches, cabling, system setup) - Server and workstation hardware configuration
Programming - Python (backend systems, ML deployment) - C/C++ (performance-critical systems) - C# (Unity development) - SQL (database design and normalisation)
Professional Experience
Researcher (AI Systems / MLOps Focus)
Kingston University, London | 2021 – Present
- Designed and deployed containerised ML systems using Docker across Linux environments
- Built distributed inference pipelines using FastAPI, Celery, and Redis for asynchronous processing
- Developed production-oriented backend services for scalable AI workloads
- Optimised GPU-based inference performance for real-time applications
- Integrated ML systems into simulation and XR environments for industrial use cases
- Contributed to EU-funded projects focused on reliable and scalable AI deployment in Industry 4.0
Projects
ML Deployment Platform (Distributed System)
- Designed a scalable inference platform using FastAPI, Celery, and Redis
- Implemented asynchronous task queues and distributed processing
- Containerised services for reproducible deployment
Cloud & Service Deployment
- Deployed services on AWS (EC2) for remote access and hosting
- Integrated Azure AI services into production workflows
Containerised AI Systems
- Built Docker-based ML services for real-time inference
- Managed dependencies and runtime environments across Linux systems
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
Available on request (focused on computer vision and efficient AI systems)
Additional
- Experience with VR/AR systems (Unity, Unreal Engine, HoloLens)
- Exposure to robotics systems (Unitree platform, Python-based control)