Tinder 6 дней назад
Staff Engineer, Applied AI
225 000 – 265 000 $в год
- Palo Alto, California, USA
- Гибрид
- Опыт от 8 лет
- Полная занятость
PythonAITypeScriptLLMBackendinfrastructureOAuthOIDCPlatformRBACABAC
Описание
Responsibilities
- Work closely with internal teams to build real solutions for challenges they are facing day to day.
- Own the design of the agent platform across gateway, connectors, identity, policy, guardrails, observability and cost, and write the roadmap for how it evolves.
- Design identity and delegation for agents: acting on behalf of a user, agent-owned identities for unattended jobs, short-lived scoped credentials, and every action traceable to a responsible human.
- Build access control beyond tool allowlists: per-action, per-argument and per-data-class policy, human approval for irreversible actions, and policy that's reviewable and tested.
- Build guardrails enforced at the tool boundary, not in prompts, against prompt injection through tool output, confused-deputy access, data exfiltration and over-broad scopes.
- Make agent behavior observable: traces of tool calls and decisions, audit trails investigators can use, evals that catch regressions when models or prompts change, and per-team cost attribution.
- Set the bar for connectors and third-party MCP servers: onboarding, review, versioning, sandboxing and safe defaults.
- Run the platform as production and own its on-call: latency budgets, failure modes, rate limits and quotas, kill switches and incident response.
- Partner with Security, our forward deployed engineers and platform teams, and mentor the engineers who build on and contribute to the platform.
Requirements
- Great communication and collaboration skills, experience working with real challenges of customer
- 8+ years building backend, infrastructure or platform systems that other teams depend on, with recent hands-on work on LLM agents, tool use or MCP.
- Experience shipping identity or authorization systems: OAuth 2.0 and OIDC, token exchange or delegation, service identity, and policy models (RBAC, ABAC or relationship-based).
- An attacker's mindset about agent systems, and the ability to explain why prompt-level defenses aren't enough.
- Experience operating gateways, proxies or other services in the critical request path, including on-call, observability and incident response.
- Strong skills in Python or TypeScript, and daily use of AI coding tools with a clear sense of where they fail.
- A track record of working well with security teams and impatient internal customers, turning "no" into a safe "yes, like this."
Nice to have
- Experience with policy engines or workload identity.
- Built or operated an LLM gateway, model router or MCP server in production.
- Familiarity with OpenTelemetry and tracing for non-deterministic systems.
- Contributions to agent identity or MCP authorization standards.
- Engineering background in application protection, identity and access management, or threat detection and incident response.
We offer
- Salary Range: $225,000 - $265,000 a year
- Factors such as scope and responsibilities of the position, candidate's work experience, education/training, job-related skills, internal peer equity, as well as market and business considerations may influence base pay offered.
- This salary will be subject to a geographic adjustment (according to a specific city and state), if an authorization is granted to work outside of the location listed in this posting.
- Parental Leave: 100% paid parental leave (including for non-birthing parents) and family forming benefits
- Plan for the Future: 100% 401(k) employer match up to 10%, Employee Stock Purchase Plan (ESPP)
- Personal Growth: Mentorship through our MentorMatch program, access to 6,000+ online courses through Udemy, and an annual stipend for your professional development
- Give back: Time off to volunteer and charitable donations matched up to $15,000 annually
- Investment in your wellness: Access to mental health support via Modern Health, paid concierge medical membership, pet insurance, fitness membership subsidy, and commuter subsidy
- Flexible Vacation: With no waiting period and 10 annual wellness days