Senior Backend & Infra Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Senior Backend & Infra Engineer (AI): Architect and build distributed backend systems and agentic services powering real-time messaging, scalable APIs, and autonomous AI agent runtimes with an accent on LLM orchestration, memory/retrieval infrastructure, and production reliability at scale. Focus on designing event-driven, highly concurrent real-time architectures and end-to-end backend logic (databases, APIs, performance tuning) while raising the technical bar through RFCs, reviews, and mentorship.
Company
builds AI-powered video creation technology.
What you will do
- Architect and build scalable distributed backend, infrastructure, and agentic services for web, mobile, and multi-platform products.
- Design and optimize the agent runtime execution loop (reasoning, tool-use frameworks, function calling, memory retrieval, multi-step orchestration).
- Own and scale real-time messaging and event-driven systems (WebSockets, pub/sub, throughput/latency/reliability).
- Implement core AI capabilities including LLM integrations, multi-provider model routing, context window management, cost optimization, and streaming responses.
- Build memory and retrieval systems using semantic search and vector/embedding infrastructure for long-term and episodic recall.
- Drive backend logic end-to-end: database modeling (SQL/NoSQL), API design, performance tuning, and production reliability; lead technical excellence via RFCs, code reviews, and mentorship.
Requirements
- 5+ years of software engineering experience building production services at scale, with 2+ years hands-on with LLM-based orchestration, multi-agent systems, or agentic solutions.
- Deep proficiency in modern backend technologies and frameworks (Node.js, Python, Go; Express, FastAPI, TypeScript, etc.).
- Strong distributed systems and infrastructure knowledge: event-driven microservices, message queues, AWS/GCP, Kubernetes, and CI/CD.
- Solid understanding of LLM capabilities/limitations and agentic prompting and execution (system prompts, structured output, tool-use execution, embedding models).
- Comfort designing and debugging real-time streaming pipelines, long-polling, and highly concurrent networking.
- Ownership mindset with strong communication and collaboration across engineering and product teams.
Nice to have
- Experience with multi-modal AI architectures (image generation, TTS, speech-to-text, video generation).
- Experience with agent frameworks (LangChain, CrewAI, AutoGPT) or building custom high-performance execution runtimes.
- Experience with fine-tuning, RLHF, or DPO pipelines.
- Background in multi-tenant SaaS or internal tooling and operational automation.
- Previous startup experience and strong competitive coding background.
Culture & Benefits
- On-site role at ’s Palo Alto HQ, working from the office 3–5 days a week.
- Comprehensive health benefits and monthly stipends.
- Equity in a fast-growing startup.
- Company retreats and a supportive, collaborative office culture.
Hiring process
- Technical evaluation through interviews and code/review-style discussions.
- Assessment of system design, AI/agentic architecture, and ownership mindset.
Location: Palo Alto HQ (On-site)
Salary: $185K–$300K
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 →