• Ship the agent platform to production including an event-triggered queue, a headless model-agnostic runtime, durable state, a human review gate, atomic rollback, and complete run logging in the warehouse • Own the evaluation layer, including golden suites with behavioral assertions, judge criteria with a written rubric, safety cases, and a CI gate that blocks regressions • Build and register the agent portfolio across reporting, drafting, linting, triage, and question-answering agents, plus a meta layer that observes and improves the platform • Enforce governance in code with risk tiers, least-privilege credentials, tool-permission gates, a decision audit log, and autonomy classes • Design how the system contacts people with a hard interruption budget, message bundling, and useful structures • Own the platform tooling including the compiler, validator, inventory integrity, and distribution paths for context and capabilities • Compute operating measures from production data to generate a maturity grade per team • Instrument the platform’s own return with a ledger that logs the work each agent absorbs and computes monthly figures •
• Have shipped production LLM agent systems that other people depended on with operational history, real users, and incident experience • Design evaluations rather than spot checks, building golden sets, writing behavioral assertions, defining judge rubrics, and gating CI on results • Have done deep API work against systems work actually lives in and have authored MCP servers • Own infrastructure end to end in Python on GCP with a cloud warehouse and infrastructure as code • Have taste about how software contacts humans, treating every notification as spending a limited amount of trust •
• Fully Remote work environment with WeWork membership or co-working allowance • ESOP (equity ownership) in the company • Tech Allowance to set up an ideal work environment • Health benefits covering 100% of health insurance for employees and 80% for dependents • Annual Off-Sites where the entire company gathers in a new city for a week • Flexible Work operating asynchronously • Professional Development with an annual education allowance •
• Python • GCP • Infrastructure as Code • MCP • LLM •
Kerjaaa.org tidak memungut biaya apapun & pencari kerja disarankan untuk menghindari pihak yang meminta pembayaran saat melamar kerja.
Job post ini diupload oleh kerjaaaorg. Hubungi halo@kerjaaa.org jika menemukan job post yang mencurigakan, atau ingin job ini diturunkan.
This job post is uploaded by kerjaaaorg. Contact us at halo@kerjaaa.org to submit your job openings, find inaccuracy, notice a fraud or to takedown this post.
We are on Telegram to share jobs weekly. Join our official channel!
