DevOps Engineer - AI Platform & GPU Infrastructure
Proto · Karachi
Description du poste
About the role
Proto, a Canadian-registered AI communication platform, is hiring a DevOps Engineer to manage, scale and secure the cloud and infrastructure behind its AI agent platform, which serves governments, regulators and businesses in emerging markets. The role covers infrastructure as code, CI/CD pipelines, cloud infrastructure and site reliability, and includes deploying and managing GPU infrastructure for AI workloads and supporting enterprise on-premise deployments. It is a lean, remote-first team.
Key responsibilities
- Build and maintain resilient cloud infrastructure, GPU environments and automated release pipelines, including enterprise and on-premise deployments.
- Design and maintain scalable cloud infrastructure with IaC tools such as Terraform.
- Develop and optimise CI/CD pipelines for high availability and zero-downtime releases.
- Manage Kubernetes clusters, container orchestration and microservices across cloud and on-premise environments.
- Deploy, configure and optimise GPU infrastructure (NVIDIA GPUs, CUDA, GPU drivers) and support AI model, LLM inference and GPU-accelerated applications.
- Assist with infrastructure sizing, GPU resource allocation and performance tuning.
- Lead customer deployments in on-premise and private cloud settings, including restricted or air-gapped networks.
- Package and deploy containerised applications with Docker and Docker Compose, including Kubernetes.
- Troubleshoot deployment issues with customer IT teams (networking, firewalls, proxies, storage).
- Implement monitoring, logging, tracing and alerting; drive SRE practices, incident management and automated failover/recovery.
- Work with development, security and QA teams on DevSecOps and infrastructure security.
Required profile
- 3+ years of experience in DevOps, Cloud Engineering, Infrastructure Engineering or SRE.
- Proven track record with Infrastructure as Code (Terraform) and automated CI/CD pipelines.
- Hands-on experience with Linux servers and production infrastructure.
- Experience deploying applications across cloud, private cloud or on-premise environments.
- Strong troubleshooting skills across infrastructure, networking, storage and application deployment.
Required skills
- AWS, Kubernetes, Docker and Infrastructure as Code (Terraform)
- Python and Bash scripting
- Monitoring and observability tools such as Prometheus, Grafana, Datadog and ELK
- Service mesh, ingress control and networking fundamentals (DNS, VPN, load balancing, firewalls, reverse proxies)
- Nice to have: GPU infrastructure (CUDA, DCGM), AI/ML model deployment (vLLM, Ollama, Triton, Hugging Face TGI), VMware/Proxmox, and experience with regulated or air-gapped environments
Questions fréquentes
Pourquoi signalez-vous cette offre ?
Aller plus loin
Salaires, guides et recherches au Canada.
Postulez en 30 secondes
Entrez votre email pour postuler. Un compte sera cree automatiquement.
En continuant, vous acceptez nos conditions d'utilisation.
Deja un compte ? Connexion
Une question sur cette offre ?
Posez-la ici : vous recevrez le récapitulatif de l'offre par e-mail, tout de suite.
Publie il y a 17 heures
Expire dans 1 mois
11 vues · 0 interesses
Boostez vos chances
Importez votre CV : nous vous proposons les offres qui matchent votre profil.
Analyse de votre CV en cours...
Proto
Karachi