Роль дает заметную ответственность в развивающемся продукте на стыке ИИ и безопасности, но зарплата ниже рыночной медианы, а для начала работы нужно лично приехать в Сан-Франциско.
Кликните для подробной информации
Ниже рынкаСовременный стекИИ и безопасностьЧеткая зона ответственностиОнбординг в офисе
Оценка от Hirify AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Staff Software Engineer (Applied AI): Building reliable autonomous digital workers and the harnesses, evaluations, and model integrations that support identity operations and security with an accent on agent execution, verified actions, and production reliability. Focus on testing prompt injection and unsafe tool use, measuring model quality and cost, and turning production failures into regression tests.
Location: San Francisco, California; in-person onboarding is required
Annual base salary: $194,000–$267,000 USD for candidates located in the San Francisco Bay Area.
Company
Okta provides identity and security infrastructure for organizations and is developing autonomous AI agents for identity operations.
What you will do
Build agent harnesses for planning, tool use, memory, context compaction, interruption, recovery, and long-running execution.
Integrate OpenAI and Anthropic model APIs and select models based on quality, latency, cost, and failure handling.
Connect agent harnesses to AWS workflow execution and approval state.
Enforce authorization and application policy checks, requiring evidence of resulting state before completing work.
Build evaluation datasets, replay tests, and analytics for findings, access decisions, application setup, and agent onboarding.
Test prompt injection, stale evidence, conflicting instructions, unsafe tool use, and tenant-boundary protection.
Requirements
Strong Python engineering skills and experience shipping LLM applications that use tools.
Hands-on experience building agent workflows or evaluation systems for tool-using LLM applications.
Experience integrating model APIs, structured outputs, and asynchronous services, especially OpenAI or Anthropic.
Depth in agent execution or evaluation systems, including working code and failure analysis.
Ability to distinguish plausible model responses from supported findings or verified actions.
Staff-level ownership of a domain such as harnesses, evaluations, or model quality.
Nice to have
Open-source contributions, agent observability, security evaluations, or synthetic evaluation data.
Experience with fine-tuning, preference data, post-training evaluation, or model distillation.
Experience with identity and security workflows or foundation-model research.
Culture & Benefits
Startup-like ownership and execution pace with the resources of a public company.
Direct opportunity to shape products used by Okta’s 20,000+ customers.
Health, dental, and vision insurance, 401(k), flexible spending account, paid time off, and parental leave.
Equity and bonus opportunities where applicable.
In-person onboarding designed to connect new hires with the mission and team.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →