Senior Platform & SRE Engineer (On-Prem & AI Systems)

Senior Platform & SRE Engineer (On-Prem & AI Systems) Location: Bengaluru / Hybrid Team: Platform Engineering & Infrastructure We are building lean, agentic AI systems and enterprise-grade developer platforms designed for IT and DevOps teams who need reliable, secure, and cost-efficient AI deployments. Our products run in cloud, hybrid, and fully on-prem environments , enabling enterprises to streamline testing, monitoring, compliance, and operational efficiency. As a Senior Platform & SRE Engineer (On-Prem & AI Systems) , you will own the infrastructure layer that powers all our AI services. You will design scalable, secure, and fault-tolerant environments, orchestrate on-prem deployments for enterprise customers, and ensure platform reliability across cloud + customer VPC setups. This role sits at the intersection of infrastructure engineering, DevOps, SRE, and AI system deployment . You will define the platform architecture, build automation, improve observability, optimize performance, and work closely with product and ML teams to enable fast, reliable delivery of our AI-driven features. This role is for engineers who think in systems, automate everything, and thrive in environments where reliability, security, and efficiency are non-negotiable. What You’ll Own End-to-end infrastructure architecture for cloud and on-prem deployments Scalable, reproducible deployments of AI, ML, and microservice workloads SRE responsibilities : uptime, SLO/SLA definitions, incident response, postmortems Build and manage CI/CD pipelines , GitOps workflows, automated release processes Implement observability stacks (OpenTelemetry, Prometheus, Grafana, ELK) Optimize platform performance, CPU-based model serving, cost efficiency Security-first infrastructure design: secrets, IAM, isolation, least-privilege access Create reusable Terraform/Helm/Ansible modules Collaborate with backend, ML, and product teams on platform-level decisions Drive operational excellence across monitoring, reliability, and scalability What You’ll Bring Must-Have Skills 5+ years in Infrastructure, SRE, or DevOps roles Deep experience with on-prem deployments (VMs, proxies, firewalls, private networks) Strong Terraform / Helm / Kubernetes (EKS, GKE, self-managed clusters) Observability expertise: Prometheus, Grafana, OpenTelemetry CI/CD expertise: GitHub Actions, GitLab CI, ArgoCD, or similar Strong Linux fundamentals, networking, Docker internals Experience deploying distributed microservices in production Ability to debug infrastructure issues end-to-end Great-to-Have Experience supporting AI/ML workloads , model serving, vector DBs Familiarity with open-source LLMs and CPU-based inference optimizations Experience with air-gapped/on-prem enterprise deployment models Security certifications or experience with SOC2 / enterprise compliance Performance engineering, scalability tuning, load testing Why This Role Matters You will be one of the most critical hires in shaping our core platform - the foundation on which our agentic AI systems operate. Your work will determine how fast we can innovate, how reliably we can operate, and how securely we can deploy AI in enterprise environments. You will directly influence: Our Managed and on-prem enterprise architecture Product reliability & SLAs Deployment experience for customers Overall developer velocity and system scalability This is a career-defining opportunity to build a next-generation AI platform used by enterprise IT and DevOps teams globally.