PLAI is an AI platform for racquet sports (tennis, padel) that transforms any court into a smart playing space with video, analytics, and tournaments.
We are building a system that:
- processes video from cameras in real time
- runs ML/Computer Vision models
- scales for thousands of matches
- unites players into a single digital ecosystem
We are currently looking for a DevOps / MLOps Engineer to help build and scale the infrastructure for our AI product.
Your responsibilities
- Designing and developing PLAI's cloud infrastructure (considering ML workloads)
- Deploying and maintaining a microservices architecture
- Building CI/CD and ML pipelines (CI/CD/CT for models)
- Automating ML model deployment and updates
- Managing Kubernetes clusters (including GPU workloads)
- Setting up monitoring for:
- infrastructure
- services
- ML models (drift, latency, quality)
- Optimizing video/data storage and processing
- Participating in load testing (including inference load)
- Ensuring security (data, models, APIs)
- Responding to incidents and improving system stability
What is important
- Solid Linux (Ubuntu) experience
- Hands-on experience with Docker and Kubernetes (production)
- Experience building CI/CD (GitLab CI or similar)
- Experience with cloud platforms (AWS / GCP / Yandex Cloud / Azure)
- Understanding of networking: DNS, load balancing, CDN
- Experience configuring Nginx under load
- Experience with monitoring (Prometheus / Grafana / ELK / Zabbix)
+ MLOps part (mandatory):
- Experience deploying ML models to production
- Understanding of the ML pipeline: training → validation → deployment → monitoring
- Experience working with:
- MLflow / Kubeflow / Airflow / equivalents
- Understanding of data handling:
- data and model versioning
- GPU experience (preferred)
- Understanding of ML challenges in production:
- data drift
- model degradation
- inference latency
A big plus would be
- Experience with computer vision / video processing
- Work with real-time systems
- Kubernetes Ingress / Service Mesh
- Infrastructure as Code (Terraform / Ansible)
- Experience configuring CDN / edge (e.g., Cloudflare)
- Experience building data pipelines
Why it's interesting
- You are building the infrastructure for an AI product, not just a backend
- Real-world tasks:
- video
- computer vision
- real-time inference
- Work at the intersection of DevOps + ML
- High impact on architecture
- Rapid growth → opportunity to become Head of Infrastructure
What we offer
- Great team
- Work on interesting tasks
- Opportunity to join the project at an early stage
- Possibility of remote work
- Good salary
P.S. We value your enthusiasm and responsible approach to work. We are a funded startup creating an interesting commercial product, and each team member's contribution to the final result is of utmost importance.
