Staff AI Engineer, Agentic Automation

🔥 45 minutes ago

🇺🇸 United States – Remote

⏰ Full Time

🔴 Lead

🤖 AI Engineer

👻 Ghost score 10%

What it means: the chance that no one is really hiring for this job.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Cerby

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2020

🔒 Cybersecurity

☁️ SaaS

Cybersecurity • SaaS

Cerby is an identity security automation platform that helps organizations secure and automate access for applications that lack standard identity integrations. It provides credential management, single sign-on (SSO) and MFA for non‑SAML/OIDC apps, identity lifecycle automation without SCIM/APIs, privileged access management for disconnected apps, and centralized controls for enterprise social media accounts, integrating with existing IAM/IAG/PAM stacks.

📋 Description

• Own agentic onboarding and self-healing end to end, including architecture, roadmap, and on-call after launch • Take existing API catalog generation and browser workflow generation systems to production on durable workflows using Temporal, with observability • Detect automation drift from failed runs before customers notice • Build agents that diagnose breaks, repair workflows or specifications, and re-validate fixes against real runs • Decide which issues heal automatically and which require human review • Own benchmarks for generated specifications, workflows, and repairs • Define measured quality thresholds for production readiness • Own cost and latency per output, selecting frontier versus open-weight models based on measured accuracy and cost • Own the threat model, including prompt injection from page content, credential isolation, token handling, sandboxed browsing, and egress • Keep credentials out of prompts, logs, queues, and stored run state • Partner with integrations, automation-runtime, and platform teams • Write design documents and mentor contributors

🎯 Requirements

• Experience shipping an LLM agent with tool use that ran unattended for real users • Experience owning a backend system in production • Strong in Python or TypeScript, and productive in both • Experience with LLM agents and tool use, including agent loops, structured outputs, retries, and failure modes • Experience building benchmarks or evaluation harnesses and using them to make decisions • Depth in browser automation (Playwright or similar) or backend and API-integration systems, and comfort in the other • Knowledge of distributed systems, including queues, idempotency, and durable workflow engines (Temporal, Step Functions, or similar) • Security judgment for systems handling secrets, including prompt injection threats • Clear technical writing and ability to make trade-offs other teams can depend on • Desirable: Temporal in production; Pydantic AI or comparable agent framework • Desirable: Open-weight model serving (Fireworks, Together, Bedrock) and LLM cost modeling • Desirable: Computer-use agents or browser extensions (Chrome MV3); OpenAPI tooling • Desirable: Identity, IAM, or credential-management experience; AWS and Terraform

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume