platform software engineer in AI infrastructure

Qdrant; United States; Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

401(k) match

Health insurance

Flexible PTO

Job summary

Qdrant ищет опытного инженера платформы для разработки и эволюции сервисов ядра и внутренних API, которые используют несколько команд. Вы будете отвечать за архитектурные инициативы и улучшение базы кода, поддерживать высокие стандарты качества и совместной работы.

Вы будете работать над миграцией gRPC, основами событий и pub-sub, улучшением контроль-плана и кластер-API, а также писать продакшн Go код и тесно сотрудничать с командами Regions & Clusters, Resilience и Features.

Qualifications

• Опыт not less 5 лет в роли инженера ПО на платформах/распределённых системах.
• Глубокие знания Go и/или Python, умение работать с двумя языками.
• Опыт проектирования API и распределённых систем, взаимодействия между сервисами.

Responsibilities

• Разрабатывать и развивать сервисы ядра и внутренние API, используемые несколькими командами.
• Проводить архитектурные инициативы, включая миграцию gRPC, основы событий и pub-sub.
• Владеть и улучшать контроль-пла��н и кластер-API компоненты.

Skills

Go

Python

Distributed systems

API design

Communication

Tools

Kubernetes

Cloud-native architectures

Prometheus

Grafana

OpenTelemetry

Job description

Описание

Qdrant develops an open-source vector search engine that powers AI applications, including semantic search, retrieval-augmented generation, AI agents, and real-time recommendations. Its retrieval infrastructure layer supports modern AI applications.

Задачи

Design and evolve core platform services and internal APIs used by multiple teams Drive architectural initiatives, including gRPC migration, eventing and pub-sub foundations, and platform refactoring Own and improve control-plane and cluster-api components Build platform abstractions that reduce operational and cognitive load for other teams Write production-grade Go code for platform services and internal tooling Collaborate with Regions & Clusters, Resilience, and Features teams to enable delivery through platform primitives Improve platform scalability, reliability, and developer experience through thoughtful design Support production systems and incident response when needed, focusing on long-term fixes

Требования

At least 5 years of experience as a software engineer working on platform, infrastructure, or distributed systems Strong proficiency in Go and Python, or deep expertise in one and willingness to work regularly with both Solid experience with Kubernetes and cloud-native architectures Strong understanding of distributed systems and API design Experience building and operating production systems used by other engineers or teams Comfortable working across teams and driving technical alignment Ownership mindset and clear communication skills Будет плюсом: experience with gRPC, event-driven architectures, or control-plane systems; familiarity with Kubernetes operators or cluster-level abstractions; background in SaaS, database, or systems-level product companies; experience with observability tooling (Prometheus, Grafana, OpenTelemetry); contributions to open-source projects

Условия

Competitive salary with additional perks Flexible working hours and an async-friendly culture High ownership and real impact Open-source, engineering-driven culture Choose your own laptop equipment US-based full-time employees receive a benefits package including 401k match, health, dental, and vision insurance, plus flexible PTO