Part-time (15–20 hours/week) BizFi reliability owner spanning AI evaluation, automated QA, security testing, CI/CD quality gates, observability, incident response, deployment safety, drift/regression detection and DevSecOps evidence.
Own AI evaluation, Langfuse datasets/evals, regression/automation, integration and adversarial testing, CI/CD quality gates, secrets/security, Cloudflare/deployment controls, observability, incident response, load/recovery testing and tenant-isolation evidence.
Senior QA/AI reliability/DevSecOps experience; LLM evaluation, Langfuse or equivalent traces/evals, API/integration automation, CI/CD, cloud/Cloudflare, secret management, monitoring/alerting, security testing, backup/recovery and incident investigation.