Staff Software Engineer, Agentic Tools

This is a fully remote position, open to applicants in California.

📋 Description

• Design, construct, and manage production agentic workflows and platform harnesses.

• Engage in intent engineering by converting goals into specifications, rules, constraints, and acceptance criteria.

• Remain updated on AI tools and practices while promoting effective methodologies throughout Engineering.

• Take part in design discussions and execute the agreed-upon solutions.

• Develop observability and guardrails, which include tracing, regression detection, human-in-the-loop controls, safe rollouts, and operability.

• Oversee agent runtime components such as job isolation, scheduling, execution environments, secrets, access, and cloud production operations.

• Design and manage event-driven architectures utilizing queues, streams, webhooks, and asynchronous job fan-out.

• Sustain automated CI/CD paths with progressive delivery and rollback capabilities.

• Utilize and enhance the platform through dogfooding.

• Enhance AI-assisted engineering workflows for writing, testing, reviewing, debugging, and validating changes.

• Collaborate across Engineering to comprehend workflows, deliver tools, and promote adoption through playbooks, examples, demos, and enablement.

• Assess build-versus-buy decisions and keep track of the AI tooling ecosystem.

• Define and monitor adoption, quality, reliability, and satisfaction metrics.

• Partner on security and data access initiatives.

• Guide projects from design through implementation, rollout, and ongoing operability.

• Participate in standby, on-call, or off-hours responsibilities as necessary.

⛳️ Requirements

• Staff-level (or equivalent) professional software engineering experience in building and operating production distributed systems.

• Proficient in TypeScript and modern JavaScript.

• Experience with Node.js for deploying production services.

• Solid software engineering fundamentals related to design, testing, debugging, APIs/services, and code quality.

• Familiarity with automated pipelines, progressive delivery or safe rollout, monitoring, and rollback processes.

• Hands-on proficiency with modern LLM and agentic coding workflows in production or substantial internal platforms.

• Experience in developing backend services, integrations, automation, and internal tools.

• Professional background in agent orchestration, tool-calling systems, evaluation or guardrail techniques, and connecting agents to reliable backend systems.

• Knowledge of agent frameworks, orchestration layers, and integrating external tools and data sources into LLM-based systems.

• Experience with event-driven systems such as queues, streams, pub/sub, or webhooks.

• Proficient in observability with metrics, logs, and traces.

• Strong communication, documentation, and teaching skills.

• Good judgment regarding security, permissions, data access, and safe tool rollout.

• Ability to solve problems from first principles, make informed trade-offs, and work independently through ambiguity.

• Hands-on experience with Kubernetes in production (preferred).

• Familiarity with Terraform or similar infrastructure-as-code tools (preferred).

• Experience with Temporal or other workflow platforms (preferred).

• Deeper understanding of AWS/cloud-native operations (preferred).

🏝️ Benefits

• Health insurance

• Dental insurance

• Vision insurance

• Short-term disability insurance

• Life insurance

• Paid holidays

• Paid time off

• Fertility treatment benefit

• 401(k)

• Equity

• Cribl Corporate Bonus Program