Note: The job is a remote job and is open to candidates in USA. 24-MAG LLC connects experienced professionals with remote consulting opportunities across technical, evaluation, and project-based workstreams. This role involves designing cloud-infrastructure tasks and reinforcement-learning environments that evaluate AI systems across platform engineering, distributed systems, security, scalability, troubleshooting, and recovery. The Senior Platform Engineer will also create reproducible environments, automated tests, reference solutions, and defective variants based on hands-on production infrastructure experience.
Responsibilities
- Create realistic infrastructure tasks involving production-grade cloud systems
- Develop scenarios spanning distributed systems, networking, security, scalability, and reliability
- Define technically meaningful success criteria
- Incorporate practical production constraints into benchmark scenarios
- Design tasks that require substantive infrastructure reasoning
- Apply platform-engineering expertise to complex infrastructure problems
- Evaluate architecture across compute, storage, networking, and service layers
- Analyse trade-offs involving reliability, scalability, security, and maintainability
- Design realistic system topologies
- Support technically rigorous infrastructure evaluation workflows
- Develop scenarios involving scalable APIs and distributed services
- Evaluate queues, autoscaling, durable storage, and service coordination
- Model partial-failure and degraded-service conditions
- Assess distributed-system behaviour under realistic workloads
- Identify weaknesses affecting resilience or scalability
- Apply hands-on experience managing production platforms
- Design environments reflecting real operational constraints
- Evaluate deployment, scaling, security, observability, and recovery workflows
- Incorporate practical incident and failure patterns into tasks
- Use production experience to strengthen benchmark realism
- Build reproducible and containerised infrastructure environments
- Create valid reference solutions
- Develop intentionally defective variants for evaluation
- Define consistent environment setup and execution requirements
- Ensure technical tasks can be reproduced reliably
- Develop deterministic integration tests
- Create load and scalability tests
- Build security and access-control validation
- Implement failure-injection, deployment, and recovery tests
- Verify infrastructure configuration, topology, and runtime behaviour
- Design scenarios involving private networking and service connectivity
- Apply IAM and least-privilege principles
- Evaluate service-to-service security
- Identify insecure or overly permissive access patterns
- Validate network and identity configurations against task requirements
- Incorporate logging, metrics, tracing, and operational telemetry
- Define measurable SLOs and reliability criteria
- Evaluate system behaviour during failure conditions
- Design tasks requiring observability-driven troubleshooting
- Assess whether infrastructure provides sufficient operational visibility
- Develop scenarios involving rolling deployments
- Evaluate rollback strategies
- Design disaster-recovery and restoration tasks
- Assess infrastructure response to failed releases or degraded services
- Validate recovery mechanisms and resilience assumptions
- Write infrastructure automation or testing tools
- Develop utilities for environment setup and validation
- Debug containerised systems
- Support repeatable provisioning and teardown workflows
- Apply relevant programming languages to infrastructure automation
- Create environments that test AI decision-making across infrastructure workflows
- Define measurable task requirements
- Build golden reference implementations
- Construct defective or adversarial variants
- Support reliable evaluation of multi-step technical reasoning
- Review tasks developed by other experts
- Identify ambiguity, unrealistic assumptions, or validation gaps
- Assess technical correctness and benchmark difficulty
- Improve reproducibility and grading reliability
- Maintain strong engineering-quality standards across project deliverables
Skills
- Senior-level experience in cloud infrastructure, platform engineering, DevOps, systems engineering, or SRE
- Demonstrated personal ownership of a production platform or production infrastructure
- Strong knowledge of distributed systems
- Experience with scalable APIs
- Strong understanding of queues, autoscaling, durable storage, and partial-failure scenarios
- Practical IAM and least-privilege experience
- Strong knowledge of private networking and service-to-service security
- Experience with observability and measurable SLOs
- Experience with rolling deployments and rollback strategies
- Familiarity with disaster recovery and resilience engineering
- Ability to write infrastructure automation or testing tools
- Strong debugging skills in containerised environments
- No prior AI-training or model-evaluation experience is required
- Experience with Terraform or OpenTofu is advantageous
- Experience with AWS, Azure, GCP, Kubernetes, or multi-cloud infrastructure is valuable
- Background building internal developer platforms, edge infrastructure, or shared platform services is beneficial
- Experience with chaos engineering, fault injection, local cloud emulators, or resilience testing is advantageous
- Experience creating technical evaluations, automated grading systems, or AI environments is helpful but not required
Benefits
- Fully remote
- Payment made per task that meets project specifications
Company Overview