Senior ML Infrastructure Engineer (DevOps)

About the role

We are seeking a Senior ML Infrastructure Engineer who thrives on running production‑grade systems. You will partner directly with applied scientists, taking their models from prototype to reliable, real‑time inference for millions of users. The role is fully remote within Georgia, with optional access to our modern offices in Tbilisi, Batumi or Kutaisi.

Key responsibilities

• Maintain real‑time inference services, handling alerts, live debugging, incident resolution, rollbacks and post‑mortems as part of a 24×7 on‑call rotation.
• Design, build and evolve AWS infrastructure using IaC, CI/CD pipelines, Kubernetes, Docker, autoscaling, monitoring and cost‑control mechanisms.
• Manage the GPU fleet: NVIDIA driver and CUDA upgrades, node provisioning, debugging and capacity planning.
• Automate user access, SSH credentials, service accounts and developer environments for the science team.
• Run streaming data pipelines, feed an online feature store and serve low‑latency endpoints.
• Orchestrate batch workloads with Airflow or Databricks Workflows.
• Collaborate with scientists to productionise prototypes and ensure ongoing health.
• Write and review production‑grade Python code, including validation of AI‑generated snippets.

Required profile

• Proven experience in 24×7 on‑call rotations for high‑load online services, with real incidents debugged live.
• Strong Linux systems expertise and hands‑on experience with Kubernetes, Docker and Infrastructure as Code.
• Solid programming skills in Python, version control with Git and CI/CD implementation.
• Experience with workflow orchestration tools such as Apache Airflow or Databricks Workflows.
• Familiarity with generative AI development cycles (SDLC) and English proficiency at B2 level or higher.

Required skills

• Python
• Git
• CI/CD
• Kubernetes
• Docker
• AWS
• Infrastructure as Code (e.g., Terraform, CloudFormation)
• Apache Airflow
• Databricks Workflows
• Linux
• NVIDIA drivers & CUDA

What we offer

• Fully remote work within Georgia, with access to modern offices.
• Opportunities to work abroad up to two months per year.
• Leadership development, career advising and well‑being programs.
• Certification support for GCP, Azure and AWS.
• Unlimited access to EPAM’s internal learning platform and free English classes.
• Participation in the Employee Stock Purchase Plan.