Чёткая зона ответственности, фокус на прикладном ИИ и сильная компания делают вакансию привлекательной, но зарплата ниже медианы бенчмарка, а работа полностью офисная.
Кликните для подробной информации
Ниже рынкаАктуальный стекПонятная зона ответственностиИИ и кибербезопасность
Оценка от Hirify AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Software Engineer, Applied AI (Python/LLM Agents): Building reliable autonomous agents and evaluation systems for identity operations and security with an accent on tool use, model quality, authorization controls, and production reliability. Focus on designing long-running agent harnesses, measuring unsafe behavior and completion quality, protecting tenant boundaries, and turning production failures into regression tests.
Location: San Francisco, California, United States
Annual base salary: $165,000–$226,000 USD
Company
Okta builds identity and security infrastructure that helps organizations safely use AI and manage access across enterprise systems.
What you will do
Build agent harnesses for planning, tool use, memory, context compaction, interruption, and recovery during long-running tasks.
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 while evaluating existing systems and filling capability gaps.
Implement authorization and policy checks for sensitive writes and require evidence before marking tasks complete.
Build evaluation datasets, replay tests, and analytics for access decisions, risk findings, application setup, and agent onboarding.
Test prompt injection, unsafe tool use, stale evidence, conflicting instructions, and tenant-boundary issues; convert production failures into regression tests.
Requirements
Strong Python engineering skills and experience shipping an LLM application that uses 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.
Senior-level ownership of an agent capability or evaluation pipeline with measurable improvements.
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 using approved datasets.
Experience with identity and security workflows or foundation-model research.
Culture & Benefits
Startup-style ownership and execution within a public-company environment.
In-person onboarding designed to accelerate impact and build connections.
Health, dental, and vision insurance.
401(k), flexible spending account, equity where applicable, bonus, PTO, and parental leave.
Connection and collaboration across a global community spanning more than 20 offices.
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 →