platform engineer for internal AI systems

Supabase; United States; On-site; USD 160,000 - 210,000; Full time

Benefits offered by this job

Fully remote

WeWork/ко‑воркинг по всему миру

ESOP equity

Tech allowance

Health insurance 100%

Annual off‑sites

Flexible schedule

Education allowance

Job summary

HireHi ищет специалиста по разработке и эксплуатации платформы для внутренних ИИ‑агентов. Вы будете строить и развёртывать движок выполнения, систему валидации и журналирования, обеспечивать мониторинг и аудит. Опыт работы с Python, GCP и LLM‑агентами обязателен.

Работа полностью удалённая, глобальный найм, пакет ESOP и гибкий график. Будете тесно сотрудничать с инженерной командой над безопасностью и улучшением производительности.

Qualifications

• Разработал и внедрил продакшн LLM‑агент‑системы с реальными пользователями и инцидентами.
• Проектирование оценок с золотыми наборами, поведенческими утверждениями, рубриками судей и CI‑воротами.
• Опытом владения API в системах с рабочими процессами и созданием MCP‑серверов.
• Управление инфраструктурой end‑to‑end на Python в GCP: хранение данных, инфраструктура как код, развёртывание и откат.

Responsibilities

• Разрабатывать и внедрять платформу выполнения для внутренних ИИ‑агентов, включая очереди, рантайм и логирование.
• Строить уровень оценки с тестами, критериям поведения и CI‑барьерами для регрессионных запусков.
• Регистрировать агентов для отчетности, лидинга и аудита, включая мониторинг и улучшение.
• Обеспечивать Governance через уровни доступа, аудит и автономии.
• Разрабатывать уведомления и логи с учётом доверия пользователей.

Skills

Python

GCP

LLM агентные системы

CI/CD

API дизайн

Observability

Tools

MCP servers

Evaluation harness

Job description

Описание

Supabase provides a Postgres development platform with an integrated backend solution that includes Database, Auth, Storage, Edge Functions, Realtime, and Vector Search. Its globally distributed, open-source-first team builds tools for developers and supports the open-source ecosystem.

Задачи

Build and ship the execution platform for internal AI agents, including event-triggered queues, a model-agnostic runtime, durable state, human review gates, atomic rollback, and complete run logging Build the evaluation layer with golden suites, behavioral assertions, written judge rubrics, safety cases, and CI gates that block regressions Build and register agents for reporting, drafting, linting, triage, and question answering across executive, team-lead, and individual-contributor levels, as well as agents that monitor and improve the platform Enforce governance through risk tiers, least-privilege credentials, tool-permission gates, decision audit logs, and autonomy classes that make forbidden actions impossible Design systems for contacting people with per-person interruption budgets, bundled messages, and useful information provided before requests Own platform tooling, including the compiler and validator, inventory integrity, and distribution of context and capabilities to repositories and chat surfaces Compute team maturity grades from production data through a pipeline that supports query-based review of disputed results Instrument the platform’s return with a ledger that tracks work absorbed by agents and calculates monthly value

Требования

Have shipped production LLM agent systems used by others, with operational history, real users, and at least one incident to discuss Design evaluations using golden sets, behavioral assertions, judge rubrics, pass thresholds, and CI gates Have deep API experience with systems where work happens and have authored MCP servers Own infrastructure end to end in Python on GCP, including a cloud warehouse and infrastructure as code; provision, deploy, monitor, and roll back systems, and make architecture decisions Use agentic tools on real work in files and repositories, and be able to describe triggers, permissions, human approvals, logging, and a failure Be able to design software notifications with consideration for limited user trust Будет плюсом: public work in the field, such as an open-source agent framework, an MCP server, an evaluation harness, or cited writing on agent reliability; LLM observability and cost instrumentation; experience building an internal platform voluntarily adopted by non-engineers

Условия

• Fully remote
• the company hires globally
• WeWork membership or co-working allowance usable worldwide
• ESOP equity ownership
• Tech allowance for work equipment
• Health insurance covered at 100% for employees and 80% for dependents, wherever they are
• Annual company off‑sites lasting one week
• Flexible schedule in an asynchronous work environment
• Annual education allowance for courses, books, conferences, or other learning