Senior AI Platform Engineer (Multi-tenant SaaS & MLOps)(m/w/x)

Description

You will drive the evolution of scalable AI products by building robust MLOps foundations and multi-tenant SaaS architectures, ensuring high-performance delivery across the AWS infrastructure.

Requirements

• •Experience shipping and operating customer-facing SaaS
• •Ownership of end-to-end ML/AI infrastructure
• •Building self-service platforms and automated workflows
• •Track record of designing global-scale systems
• •Comfort with incident response and on-call
• •Product-focused mindset and customer value orientation
• •Strong bias for automation and robust tooling
• •Strong communication and collaboration skills
• •Knowledge of tenant isolation and protection patterns
• •Experience with OIDC/OAuth2 and tenant-aware RBAC
• •Deep Kubernetes experience and cluster operations
• •Knowledge of service mesh and ingress patterns
• •Advanced Infrastructure as Code and secrets automation
• •Experience with GitOps and progressive delivery
• •Proficiency in model lifecycle and versioning tools
• •Experience with pipeline orchestration and artifact stores
• •Knowledge of model serving and rollback strategies
• •Experience with RAG evaluation and guardrails
• •Handling streaming inference and fallback models
• •Vector DB experience and embedding lifecycle management
• •Proficiency in OpenTelemetry, tracing, and SLOs
• •Knowledge of incident management and runbooks
• •Alignment with enterprise security and GDPR requirements
• •Familiarity with SOC 2, ISO 27001, and scanning

Tasks

• •Design multi-tenant SaaS architectures
• •Ensure data and compute isolation
• •Automate tenant provisioning and onboarding
• •Manage canary rollouts and feature flags
• •Implement noisy-neighbor protection and quotas
• •Monitor per-tenant SLOs and performance
• •Deliver enterprise-grade security and audit controls
• •Build scalable, high-throughput data architectures
• •Establish robust MLOps foundations and pipelines
• •Operationalize end-to-end LLM workflows
• •Maintain unified CI/CD pipelines
• •Architect cost-efficient AWS cloud infrastructure
• •Orchestrate GPU-heavy workloads using Kubernetes
• •Optimize Docker containers for ML inference
• •Design ETL pipelines and streaming systems
• •Integrate feature stores and workflow orchestration
• •Implement comprehensive observability and drift detection
• •Embed IAM and encryption best practices
• •Automate infrastructure using Terraform and Python

Tools & Technologies

Benefits