Expert: Interactive Coding, Site Reliability Engineering (Contract, Remote)
About The Position
Patronus AI is hiring an independent contractor to work remotely with its research team on production-style reliability scenarios in a sandboxed environment. The scenarios use Kubernetes, Prometheus and Grafana, a log system, Helm, Terraform, and CI/CD. During live screen-share sessions, the contractor investigates and resolves or mitigates each scenario, explains their reasoning, points out ways the scenario differs from real operations, and helps define what a correct resolution entails. Each session is followed by a short written note describing the approach. The role contributes evaluation and training data for frontier models. Work may focus on incident response and on-call, platform and infrastructure, or observability; applicants should select the area in which they spend most of their time. The engagement is fully remote, pays $150 per hour including the paid trial session, and is expected to require about 10 hours per week for an initial 1 to 3 months, with possible extension for strong performers. Start dates are rolling, and the contractor may work from any country but needs a few hours of overlap with US or EU working hours. All solutions, notes, and reviews must be the contractor’s own work. LLM-generated code or text, copied or easily searchable scenarios, and confidential or employer/client material are not permitted. Work is evaluated for correctness, clarity of reasoning, and reviewer agreement rather than speed or volume. Hiring includes a short AI interview and resume review, a paid trial session scored against a quality checklist, and onboarding.
Requirements
- At least 3 years running production systems in at least one of the listed areas, including time on an on-call rotation within the last two years; hands-on individual contribution is required, and team management alone is insufficient.
- Hands-on experience with Kubernetes, Prometheus and Grafana or Datadog or New Relic, a log stack such as Loki, ELK, or Splunk, infrastructure as code such as Terraform and Helm, and a CI/CD system.
- Comfort with Python, Go, or Bash and reading unfamiliar codebases.
- Ability to explain reasoning aloud while working in clear professional English.
- Reliable availability for scheduled live sessions and a habit of supporting conclusions with evidence.
- All solutions, write-ups, and reviews must be original work; LLM-generated code or text is not permitted.
- Must not use copied or easily searchable scenarios or include code, configuration, runbooks, or incident details from current or former employers or clients, or anything covered by an NDA.
Nice To Haves
- Experience writing runbooks, post-mortems, SLO definitions, or incident training material.
- Familiarity with how AI coding agents fail on operations work.
Responsibilities
- Work through incident, debugging, and infrastructure-change scenarios live with a researcher.
- Read dashboards and logs, write PromQL and LogQL, fix Helm and Kubernetes configuration, roll back problematic deployments, and write post-mortems.
- Explain reasoning during work, including fixes considered and rejected.
- Review drafted scenarios and identify anything unrealistic, too easy, or underspecified.
- Help write scenario acceptance criteria, including likely incorrect actions an engineer might take under pressure.
- Write short notes after each session describing the approach and what was verified.
- Incorporate reviewer feedback within agreed turnaround times and flag guideline gaps or edge cases.
Benefits
- Paid trial session.
- Possible extension of the engagement for strong performers.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Career Level
Senior
Education Level
No Education Listed
