Staff Software Engineer (AI/LLM Platform)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Staff Software Engineer (AI/LLM Platform): Build company-wide agentic platform infrastructure that enables engineering teams to safely ship AI-powered features, with an accent on provider abstraction, safety guardrails, observability, and evaluation systems. Focus on designing stable APIs that absorb LLM/provider churn, implementing prompt lifecycle management, and architecting agent-as-a-service for long-running async workflows.
Company
builds a platform that helps families navigate senior care by connecting them with vetted senior living and home care providers.
What you will do
- Design and build agentic platform primitives and SDK components (provider abstraction, structured output validation, streaming, token management).
- Own safety and compliance infrastructure (composable guardrails, PII detection/redaction, audit logging, privacy-first observability).
- Build evaluation infrastructure for non-deterministic LLM outputs (datasets, scorers, regression detection, CI/CD integration).
- Lead churn containment by designing provider adapters and SDK architecture that withstand monthly model releases and quarterly SDK updates.
- Architect prompt lifecycle management (versioned prompt storage, CI/CD, review workflows, and integrations such as Langfuse).
- Design Agent-as-a-Service infrastructure for long-running async tasks using AWS services and collaborate with consuming teams to onboard and support them.
Requirements
- 8+ years of software engineering experience building platform infrastructure, developer tools/SDKs, or distributed systems.
- Production experience with LLM/AI systems using providers such as OpenAI and Anthropic, including handling token limits, non-determinism, outages, and model deprecations.
- Strong TypeScript expertise and experience designing APIs and abstractions for other engineers.
- Experience with AI safety/compliance: PII handling, guardrails, audit logging, and responsible AI practices.
- Experience with event-driven/async architectures (e.g., EventBridge, SQS or similar) and distributed observability (metrics, tracing, alerting).
- Strong communication and technical writing skills for internal customers across multiple teams.
Culture & Benefits
- Remote work.
- Base salary $160,000–$190,000 plus a 10% bonus based on annual earnings.
- 401(k) with match, plus dental, health, and vision insurance.
- Paid Time Off.
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 →