Note: The job is a remote job and is open to candidates in USA. 24-MAG offers remote consulting opportunities across technical, evaluation, and project-based workstreams. The company is seeking a Senior Backend Engineer to design reproducible reinforcement-learning environments that evaluate AI systems against production infrastructure challenges. The role focuses on distributed systems, cloud infrastructure, DevOps, security, deterministic validation, failure recovery, and technical documentation.
Responsibilities
- Design realistic technical environments for evaluating AI systems
- Create infrastructure scenarios involving deployment, troubleshooting, scaling, and recovery
- Define clear technical requirements, constraints, and expected outcomes
- Build reproducible environments suitable for deterministic evaluation
- Develop scenarios that reflect authentic production engineering challenges
- Design scenarios involving production-grade distributed systems
- Work across networking, service communication, queues, and durable storage
- Evaluate infrastructure architecture for reliability, scalability, and resilience
- Apply sound systems-design principles to realistic cloud environments
- Incorporate operational failure modes into environment design
- Develop scenarios involving Identity and Access Management
- Evaluate authentication, authorisation, permissions, and access-control decisions
- Incorporate infrastructure security considerations into technical environments
- Identify common configuration or security failure modes
- Ensure environments reflect realistic production-security requirements
- Develop deterministic validation tests for technical environments
- Create golden reference solutions demonstrating correct implementation
- Define reliable acceptance criteria for AI-generated solutions
- Ensure environments produce consistent and reproducible evaluation outcomes
- Validate both expected behaviour and failure conditions
- Create intentionally defective environment variants
- Design failure scenarios involving infrastructure, networking, storage, or deployment issues
- Test recovery strategies and troubleshooting approaches
- Evaluate disaster-recovery and fault-tolerance behaviours
- Ensure scenarios meaningfully test operational engineering judgement
- Apply DevOps practices to environment creation and maintenance
- Work with CI/CD pipelines and infrastructure automation
- Develop scalable and repeatable deployment workflows
- Incorporate observability and operational monitoring where relevant
- Build maintainable systems suitable for repeated technical evaluation
- Document architecture, operational flows, assumptions, and edge cases
- Produce clear technical explanations supporting environment reproducibility
- Collaborate with technical leads and project participants
- Refine specifications and acceptance criteria based on feedback
- Communicate technical trade-offs and design decisions clearly
Skills
- Strong professional backend-engineering experience
- Proven expertise in one or more of C++, Python, Rust, GoLang, Java, or JavaScript
- Strong practical experience with DevOps and cloud infrastructure
- Experience with CI/CD pipelines and infrastructure automation
- Demonstrated ability to architect, scale, and secure distributed systems
- Deep understanding of networking concepts
- Strong knowledge of Identity and Access Management
- Experience with message queues and durable storage systems
- Familiarity with observability, monitoring, and operational diagnostics
- Strong understanding of rolling deployments and disaster recovery
- Experience troubleshooting production-grade systems
- Ability to design deterministic tests and reproducible technical environments
- Strong technical documentation and communication skills
- No prior AI-training or model-evaluation experience is required
- Independent contractor engagement
- Fully remote
- Expected commitment: approximately 20 hours per week
Benefits
- Fully remote
- Independent contractor engagement
Company Overview