Software Engineer II (AI Security)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Software Engineer II (AI Security): Building and implementing security foundations for Copilot AI to ensure trusted and safe user experiences with an accent on secure orchestration, prompt injection defenses, and privacy-first systems. Focus on designing secure agentic workflows, implementing information-flow reasoning, and mitigating emerging adversarial threats in large-scale distributed environments.
Location: Must be based in Redmond, United States (Hybrid: expected to work from the office at least four days per week for those within 50 miles of the office).
Salary: $100,600 – $199,000 per year
Company
develops trusted, resilient, and safe AI experiences that scale globally across various ecosystems.
What you will do
- Develop security features to protect Copilot from prompt injection, adversarial manipulation, and unsafe agentic workflows.
- Implement secure orchestration components for safe action delegation across devices and platforms.
- Build intelligent agents using information-flow reasoning, guardrails, and security constraints.
- Collaborate with cross-functional teams in engineering, product, and privacy to adopt secure agentic patterns.
- Monitor agentic AI security metrics to enhance reliability and user trust.
- Create technical documentation for safe-delegation guidelines and risk considerations.
Requirements
- Bachelor's Degree in Computer Science or related field.
- 2+ years of technical engineering experience with coding in C, C++, C#, Java, JavaScript, or Python.
- Experience building production-quality software systems.
- Ability to collaborate effectively and communicate complex technical concepts across teams.
Nice to have
- Master's Degree in Computer Science or related field.
- Experience with large-scale distributed systems or services (1-2+ years).
- Background in security-critical, privacy-sensitive, or AI-powered systems.
- Familiarity with agentic AI concepts like tool calling or multi-agent workflows.
- Knowledge of Docker, Kubernetes, or distributed compute frameworks.
- Experience with LLM observability tools (e.g., LangFuse, MLFlow, Phoenix).
Culture & Benefits
- Growth-oriented environment emphasizing respect, integrity, and accountability.
- Opportunity to work on transformative products impacting hundreds of millions of users.
- Culture of inclusion and a commitment to empowering every person and organization.
- Standard corporate benefits package available.
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 →