We are looking for an experienced DevOps/SRE Engineer to architect, build, and maintain a resilient, scalable, and highly available infrastructure for our company’s AI-powered EdTech platform. You will play a key role in ensuring fast, reliable, and high-quality delivery across our entire technology stack:

• Flutter mobile applications (iOS & Android)

• FastAPI backend services

• GPU-accelerated ML/LLM workloads

• Next.js web portal with a Firebase backend

This position requires deep expertise in CI/CD, MLOps, cloud-native infrastructure, and high-traffic production systems to maintain operational excellence and platform reliability.

Key Responsibilities

I. CI/CD & Delivery Gating Systems

• Build and maintain full-stack CI/CD pipelines for Flutter mobile apps and FastAPI services.

• Implement quality gates at every stage — commit, build, test, deploy — including security checks, linting, performance tests, contract tests, and E2E tests.

• Enable immutable infrastructure and zero-downtime deployments with fast rollback strategies.

• Manage multi-environment release flows (Dev, Stage, Prod) with proper versioning and change control.

• Optimize pipelines to support large-scale, parallel deployments and artifact distribution.

II. Testing & Quality Automation

• Work closely with engineering teams to integrate automated testing across unit, integration, contract (FastAPI/OpenAPI), and end-to-end (Flutter) layers.

• Implement load, performance, and stress testing frameworks for backend and LLM services.

• Provision ephemeral, automated test environments for QA and feature validation.

III. MLOps & GPU Resource Management

• Manage GPU workloads on serverless or cloud GPU platforms (Modal, AWS, GCP), covering scaling, scheduling, and monitoring.

• Define autoscaling strategies and resource quotas for ML/LLM inference within Kubernetes.

• Integrate ML lifecycle orchestration for model training, tuning, and serving.

IV. Core Infrastructure & Scalability

• Architect and operate highly available Kubernetes clusters with multi-region redundancy.

• Implement autoscaling using HPA/VPA and custom runtime metrics.

• Ensure system resilience with chaos engineering, DR drills, and multi-zone deployments.

• Manage observability systems (Prometheus, Grafana, ELK, OpenTelemetry) for monitoring latency, GPU usage, WebSockets, Celery queues, and app performance.

• Build and maintain cloud infrastructure using IaC tools like Terraform or CloudFormation.

V. High-Traffic Systems Optimization

• Optimize FastAPI services for high concurrency and WebSocket workloads.

• Implement efficient load balancing, caching, and routing strategies to minimize latency.

• Apply rate-limiting, throttling, and backpressure for LLM-heavy API endpoints.

VI. Security & Compliance

• Enforce security best practices: encryption, secrets management, data protection.

• Ensure compliance with GDPR, HIPAA, and other relevant standards.

• Conduct vulnerability scans, penetration testing, and prepare incident-response workflows.

VII. Web & Mobile Platform Support

• Support and maintain the Next.js + Firebase web portal.

• Collaborate with mobile engineers on app performance, crash monitoring, and automated release pipelines.

Required Skills & Qualifications

• 5+ years in a DevOps or SRE role managing full-stack, high-traffic, cloud-native production systems.

• Strong expertise in Kubernetes cluster architecture and operations, especially for ML and mobile workloads.

• Proven experience building CI/CD pipelines for Flutter and REST/web backend services.

• Hands-on experience implementing quality gates and integrating automated testing at scale.

• Experience managing GPU-accelerated ML/LLM workloads.

• Solid knowledge of Python/FastAPI systems, WebSocket handling, and Celery queues.

• Proficiency with IaC (Terraform) and multi-cloud environments (AWS, GCP, Azure).

• Deep understanding of observability stacks (Prometheus, Grafana, ELK, OpenTelemetry).

• Strong knowledge of cloud security, compliance, and disaster recovery practices.

Preferred Qualifications

• Experience with mobile CI/CD tools like Codemagic, Fastlane, Shorebird.

• Familiarity with microservices communication (gRPC, message queues).

• CKA or relevant cloud certifications.

• Experience scaling LLM endpoints and GPU-heavy ML infrastructure.

• Understanding of serverless and event-driven architectures.