Our partner is hiring a Backend Systems & DevOps Engineer to create terminal bench–style problems and tasks involving agents within the backend/DevOps domain, as part of a hiring effort for its AI lab partner building advanced agent-based infrastructure. This role is ideal for engineers with deep expertise in backend infrastructure, DevOps tooling, and system automation — who are excited to design realistic environments where AI agents interact with terminal-based systems, debug services, manage deployments, and solve infrastructure-level problems autonomously.
You’re a great fit if you:
- Have 3+ years of experience in backend engineering, DevOps, or site reliability engineering (SRE).
- Are proficient in Linux, Bash scripting, and terminal-based workflows.
- Have experience designing or managing CI/CD pipelines, containerized systems (Docker/Kubernetes), and cloud infrastructure (AWS, GCP, or Azure).
- Understand backend architecture components like databases, API services, message queues, and monitoring stacks (e.g. Prometheus, Grafana, ELK).
- Have built or maintained automated deployments, observability pipelines, or complex infrastructure-as-code systems (Terraform, Ansible, etc.).
- Are skilled in debugging system failures, service crashes, config errors, or infrastructure bottlenecks.
- Are curious about autonomous agents and want to build terminal-based simulation environments to test agent reasoning, automation, and recovery abilities.
- Enjoy working independently, with a strong ownership mindset and a desire to push the boundaries of what's possible.
Primary Goal of This Role
To create terminal bench–style problems and tasks involving agents within backend and DevOps systems. These environments will simulate realistic infrastructure and operational challenges — such as debugging service failures, editing configurations, managing deployments, and resolving system alerts — and will be used to evaluate the performance, reliability, and reasoning capabilities of autonomous agents under real-world conditions.
What You’ll Do
- Build sandboxed terminal environments that simulate backend and DevOps workflows.
- Create reproducible tasks involving deployment debugging, log analysis, CI failures, monitoring alerts, or misconfigurations.
- Simulate full-stack service environments using containers, microservices, and orchestration tools.
- Collaborate with AI engineers to define reward functions, task boundaries, and performance metrics.
- Implement systems for environment resets, benchmark versioning, and task automation.
- Expand the scope of tasks to represent increasingly complex real-world DevOps scenarios (multi-service failures, rollbacks, scaling, security missteps).
Why This Role Is Exciting
- You'll help define how agents are benchmarked in backend, DevOps, and systems engineering domains.
- You’ll work at the frontier of AI x infrastructure, designing problems AI has never been evaluated on before.
- You’ll have high autonomy, creative control, and direct impact on shaping a new kind of agent benchmarking platform.
Pay & Work Structure
- You’ll be classified as an hourly contractor
- Part-time (20 hrs/week) with fully remote, async flexibility — work from anywhere, on your schedule.
