Staff Engineer

주요업무

About the Job FriendliAI is seeking a Staff Software Engineer to provide technical leadership in building the core systems behind our AI inference platforms. This role operates with broad technical scope with company-wide impact, shaping architectural decisions that affect multiple products, teams, and customer workloads. You will work at the intersection of distributed systems, AI model serving, agent execution platforms, and developer infrastructure, building foundational systems that power production-scale inference. As a Staff Engineer, you will define long-term technical direction, lead complex multi-quarter initiatives, and influence engineering decisions well beyond your immediate team. This is a deeply hands-on role with significant architectural ownership and cross-functional impact. Key Responsibilities Own and evolve the technical architecture of core components of FriendliAI’s inference platforms, operating with broad technical scope with company-wide impact. Define architectural direction for scalable, multi-tenant systems supporting high-throughput, low-latency AI inference workloads. Design and implement foundational systems for agent execution, including tool orchestration, state management, and request routing for multi-step and long-running inference workflows. Lead complex, multi-quarter technical initiatives from problem definition through production rollout, balancing performance, reliability, and cost. Establish and drive performance targets, reliability goals, and operational standards for critical infrastructure components. Make cost-aware architectural decisions across compute, storage, and networking layers based on real-world production constraints. Influence technical decisions across teams by writing design documents, leading architecture reviews, and aligning stakeholders on tradeoffs. Partner closely with Product, Research, and GTM teams to translate customer needs and product direction into durable, scalable system architectures. Act as a technical reference point during incidents and postmortems, helping teams reason about failures and improve system resilience over time.

자격요건

Qualifications Experience operating at a staff-level scope, leading ambiguous, cross-team technical initiatives and owning architecture that spans multiple systems or teams. 10+ years of professional software engineering experience, with at least 2-3 years operating at a staff-level scope. Strong experience designing, building, and operating distributed systems in production environments. Proficiency in at least one backend or systems language (e.g., Python, Go, Rust, C++), with experience building production platforms, APIs, or infrastructure. Hands-on experience with LLM inference, model serving, or AI infrastructure in real-world deployments. Proven ability to drive large technical initiatives and influence architectural decisions across teams. Strong systems thinking, debugging skills, and ability to reason about failure modes in complex systems. Excellent written and verbal communication skills.

우대사항

Preferred Experience Strong experience building large-scale backend systems in Python, including production services, APIs, or internal platforms. Experience with AI inference optimization, GPU scheduling, batching, caching, or model lifecycle management. Experience designing developer platforms or internal frameworks used by other engineers. Exposure to serverless systems, control planes, or multi-tenant SaaS architectures. Experience leading incident response for production systems.

기술스택

C++, Python, Rust, LLM

채용절차

서류 전형 → 1 차 인터뷰(Platform team lead) → 2 차 인터뷰(CTO) → 3차 인터뷰(CEO) → 최종 합격 근무 형태: 정규직 근무 환경: 유연한 원격 근무 및 필요시 오피스 출근을 병행하는 하이브리드 근무 Aggressive Compensation: 업계 최고 수준의 기본급과 성과에 따른 상한선 없는(Uncapped) 파격적인 커미션 구조 제공 Stock Option: 회사의 성장과 함께 자산 증식이 가능한 스톡옵션 부여 채용 절차는 상황에 따라 일부 변경될 수 있습니다