Назад
Company hidden
5 дней назад

Senior MaaS Backend Engineer (AI)

Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Singapore/US/Norway +4 еще
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Senior MaaS Backend Engineer (AI): Building and operating a globally distributed model-serving and billing platform with an accent on Go services, Kubernetes orchestration, multi-tenant security, and LLM inference performance. Focus on designing active-active architectures, exactly-once token metering, zero-downtime migrations, and strict SLOs for high-volume customer APIs.

Location: Singapore, SG

Company

hirify.global is a technology company providing Bitcoin mining solutions, ASIC infrastructure, datacenter operations, and AI cloud capabilities.

What you will do

  • Co-own the end-to-end MaaS platform architecture, document technical decisions, set Go and API standards, and mentor engineers.
  • Build and evolve inference gateways supporting OpenAI and Anthropic compatibility, streaming, tool calling, structured output, routing, fallbacks, and API versioning.
  • Optimize token throughput, KV and prefix caching, time-to-first-token latency, model serving, LoRA multiplexing, and Kubernetes-based autoscaling.
  • Scale regional inference pools and active-active control planes with capacity-aware failover, load shedding, load testing, SLOs, and operational runbooks.
  • Implement multi-tenant isolation, fail-closed authorization, API key and OAuth lifecycle management, quotas, rate limits, abuse controls, and zero-retention data paths.
  • Build exactly-once token metering, usage ledgers, billing reconciliation, migration tooling, distributed tracing, and cost telemetry.

Requirements

  • 8+ years of backend engineering experience, including 3+ years owning a high-traffic, multi-tenant API platform for paying customers.
  • Deep experience with Go services, production Kubernetes, Envoy, GPU-aware scheduling, PostgreSQL, Redis, and Kafka.
  • Proven expertise in multi-region active-active systems, caching, backpressure, performance engineering, and zero-downtime migrations of stateful subsystems.
  • Hands-on understanding of LLM serving, server-sent-event streaming, KV and prefix caching, TTFT, throughput, and model lifecycle management.
  • Experience with OpenTelemetry, high-cardinality analytics stores, exactly-once metering, billing reconciliation, and partial-failure scenarios.
  • Ability to design strict security and tenant-isolation controls, participate in on-call rotations, and conduct blameless incident reviews.

Culture & Benefits

  • Inclusive environment valuing authenticity and diverse perspectives.
  • Startup spirit within a fast-growing digital asset and AI technology company.
  • Personal accountability, autonomy, and opportunities to contribute to new systems and projects.
  • Training, mentoring, developmental opportunities, and welfare benefits.

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 →