Cyera 7 дней назад
MLOps Engineer
- Tel Aviv
- Опыт от 4 лет
- Полная занятость
AIKubernetesDockerCI/CDLinuxLLMAWSDevSecOpsMLTerraformAzureGCPMLOps
Описание
Responsibilities
- Design, deploy and maintain the infrastructure for model serving, LLM gateways and LLM observability, across clouds, deployment types (SaaS, customer-hosted and government clouds) and new regions.
- Own GPU infrastructure, including its capacity and cost efficiency.
- Build secure, private connectivity to LLM providers and between clouds.
- Keep our systems reliable: monitor them proactively, find and resolve issues before they affect customers, and take part in on-call.
- Automate everything, and keep up with the latest infrastructure tools: evaluate new frameworks and take the ones that prove themselves from POC to production.
- Provide the infrastructure for the Research group, including GPU clusters for training, experimentation and batch workloads.
- Support the infrastructure for all ML and AI features and workloads, for ML and AI engineers and other R&D groups.
- Keep ML and research infrastructure aligned with the company's DevOps direction and Security requirements.
Requirements
- 4+ years of experience in DevOps Engineering or Site Reliability.
- Strong experience running production infrastructure on AWS, GCP or Azure.
- Hands-on experience with Kubernetes and Docker.
- Experience with Infrastructure as Code (e.g. Terraform) and CI/CD pipelines.
- Solid networking fundamentals (load balancing, private connectivity, protocols).
- Experience building and supporting distributed, high-scale production environments, including monitoring and logging.
- Linux and scripting skills.
- A passion for ML & AI workloads, and the drive to grow in this space.
- Strong problem-solving and communication skills, and the ability to work across R&D teams.
Nice to have
- Experience running ML models or LLM-based systems in production.
- Experience with GPU workloads on Kubernetes, GPU sharing, capacity planning and cost optimization.
- Experience with LLM serving, LLM gateways or inference-aware load balancing.
- Experience deploying ML and research tooling (e.g. experiment tracking, LLM observability).
- Experience with distributed compute frameworks for large-scale inference.
- Knowledge of vector databases, embeddings or retrieval pipelines.
- Experience with customer-hosted or government cloud deployments.
- Familiarity with SOC2 / ISO 27001 requirements.
We offer
- At Cyera, we care about collaboration, innovation, and agility. We take “teamwork” seriously—with our inclusive and supportive culture at the forefront—and we’re just as serious about nurturing Cyerans to grow, both personally and professionally.
- Feel free to apply even if your experience doesn’t tick every box.
- We’re building something special here—and we welcome Cyerans with diverse backgrounds, perspectives, and experiences.