🛠 Tech Stack

💼 About This Role

You'll lead self-hosting and AI infrastructure initiatives at Observe.AI, optimizing GPU orchestration and low-latency AI deployments. You'll own end-to-end infrastructure scalability and drive MLOps best practices. This role offers strong technical leadership in a fast-scaling AI company.

🎯 What You'll Do

• Lead transition from managed to self-hosted Elasticsearch, Prometheus, Kafka
• Optimize AI/ML model deployment and scaling for high availability
• Design scalable, fault-tolerant systems for AI workloads
• Enhance CI/CD pipelines using MLOps tools like Kubeflow, MLflow

📋 Requirements

• 6+ years in DevOps, SRE, or Cloud Infrastructure
• Strong expertise in Kubernetes (EKS, AKS) for GPU clusters
• Experience self-hosting Elasticsearch, Prometheus, Kafka
• Hands-on with Infrastructure as Code (Terraform, CloudFormation)

✨ Nice to Have

• FinOps expertise for GPU cloud compute cost optimization
• Familiarity with service meshes (Istio, Linkerd)
• Knowledge of compliance frameworks (SOC2, ISO 27001)

🎁 Benefits & Perks

• 🏥 Excellent medical insurance with free online doctor consultations
• 🎓 Learning and Development fund for continuous learning
• 📅 Generous holidays and flexible benefit plans for tax exemptions
• 👶 Parental leave policies
• 🎉 Fun events to build culture across the organization

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3System Design / Architecture· 60 min