Staff AI Engineer, Agentic Automation
New
J
JobgetherEnterprise security
Based in the United States; work remotely from anywhere in the United StatesFull-TimeStaff
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonTypeScriptPlaywrightDistributed Systems
Requirements
- Demonstrated experience shipping LLM-powered agents with tool-use capabilities for real users and owning backend systems in production.
- Strong proficiency in Python or TypeScript, with the ability to work productively in both.
- Deep understanding of agent loops, structured outputs, tool orchestration, retries, and failure modes in autonomous AI systems.
- Experience building evaluation frameworks, benchmarks, or testing harnesses and using quantitative results to improve production quality.
- Significant experience with browser automation such as Playwright, or deep expertise in backend and API integration systems, and the ability to work across both areas.
- Understanding of queues, idempotency, durable execution, and workflow orchestration platforms such as Temporal or AWS Step Functions.
- Strong security judgment for systems handling credentials and sensitive information, including prompt injection risks, secret isolation, and secure execution environments.
- Ability to take early-stage systems from development to production independently, make architectural trade-offs, and maintain reliability after launch.
- Excellent technical writing skills and ability to document architecture, communicate complex decisions, influence stakeholders, and mentor engineers.
- Preferred: production experience with Temporal, Pydantic AI or comparable agent frameworks, open-weight model serving platforms, and LLM cost modeling.
- Preferred: familiarity with computer-use agents, Chrome Manifest V3 browser extensions, OpenAPI tooling, IAM, credential management, AWS, and Terraform.
Responsibilities
- Lead end-to-end architecture, development, deployment, and operation of agentic application-onboarding and self-healing automation systems.
- Define technical roadmaps and production-readiness standards, and own reliability, observability, and on-call responsibilities.
- Develop agents that analyze public API documentation and generate validated OpenAPI specifications.
- Build agents that navigate SaaS application interfaces, execute workflows, and produce replayable automation sequences.
- Design systems that detect changes in application interfaces, authentication flows, and API structures, and build agents to diagnose and repair failures.
- Establish benchmarks, evaluation harnesses, and quality thresholds for API specifications, browser workflows, and automated repairs.
- Monitor and optimize model accuracy, latency, and cost; evaluate frontier and open-weight models.
- Implement security controls for agents handling credentials and untrusted websites, including credential isolation and sandboxed browsing.
- Productionize agent systems using durable workflow orchestration and robust retry, idempotency, asynchronous execution, and failure handling.
- Collaborate with engineering teams, document technical designs, guide decisions, mentor contributors, and set production-adoption milestones.
View Full Description & ApplyYou'll be redirected to the employer's site
