MLOps Engineer

MLOps Engineer (Medior/Senior)

Location: Belgrade Office

We are looking for a talented MLOps Engineer to join our growing team!

In this role, you will primarily focus on MLOps and model deployment, while closely collaborating with our DevOps team to ensure reliable, scalable, and production-ready ML systems. You will bridge Machine Learning and DevOps, taking ownership of infrastructure, pipelines, and model operations in real-world environments.

Responsibilities (MLOps & Model Deployment – Primary Focus):

• Deploy and manage NLP models (LLMs, embeddings) and ML models (PyTorch) using tools like vLLM, TGI, Triton, Ray Serve and Nvidia Dynamo
• Optimize inference performance using NVIDIA TensorRT and PyTorch Dynamo (torch.compile)
• Configure GPU-enabled infrastructure and Kubernetes node pools (NVIDIA Container Toolkit)
• Manage model lifecycle (training → versioning → deployment) using MLflow or W&B
• Build and automate ML pipelines, including training, evaluation, A/B testing, and rollback strategies
• Introduce and maintain standards for ML project workflows
• Ensure full observability of ML systems in production
• Reference: vmWC9pt0axRC5sTwxeiKQ9omFSckN961kTD9Ld7cUTmb_duwdspn4Pm_A84C1fDF

Responsibilities (DevOps & Infrastructure – Collaboration):

• Manage cloud and bare metal infrastructure across providers (Hetzner, Oracle Cloud, GCP)
• Design, maintain, and optimize Kubernetes clusters and Docker-based workloads
• Automate workflows using CI/CD pipelines (GitHub Actions, GitLab CI) and IaC tools (Terraform, Ansible)
• Configure secure networking (VPN, Firewalls, Load Balancing) and ensure data security
• Implement and maintain observability systems (Prometheus, Grafana, logging stacks)
• Take ownership of infrastructure reliability, scalability, and performance
• Participate in on-call rotation

Technical Skills:

• Strong experience with Docker and Kubernetes
• Experience with CI/CD and Infrastructure as Code
• Knowledge of networking and security best practices
• Experience with at least one cloud provider
• Hands-on experience with MLflow or similar tools
• Solid knowledge of SQL and experience with large datasets
• Familiarity with vector databases and ETL pipeline concepts
• Experience with monitoring and observability tools (Prometheus, Grafana, ELK stack)

Profile:

• Medior to Senior level experience (3+ years of experience in a MLOps role)
• Strong sense of ownership and responsibility
• Ability to work across DevOps and ML domains
• Analytical mindset with a focus on performance and scalability
• Excellent communication skills and teamwork

What We Offer:

• Challenging projects in private sector
• Sustainable and socially beneficial projects in public sector
• Working with well-educated and experienced colleagues
• Paid certification and education in country and abroad (training, courses, exams etc.)
• Pleasant and friendly office environment
• Flexible working hours
• Parking
• Fruit, snacks and drinks
• Team buildings and Company celebrations (Secret Santa, New Year gifts for kids, Women’s Day)
• Private health care for all employees
• Paid prenatal test for pregnancy
• 100% paid sick leave
• Paid Gym & Fitness
• For the birth of a child, the employee receives 500€ bonus