Site Reliability Engineer (AI)

TL;DR

Site Reliability Engineer (AI): Ensuring the reliability, performance, and scalability of high-performance AI inference infrastructure with an accent on observability, incident management, and distributed systems. Focus on automating operational toil, optimizing GPU-backed workloads, and building resilient production-grade systems.

Company

hirify.global builds high-performance infrastructure and serverless platforms to power fast, scalable AI inference for image, video, and emerging modalities.

What you will do

• Own and improve the reliability, availability, and performance of critical production services.
• Define and evolve reliability practices, including SLIs, SLOs, and production-readiness standards.
• Investigate complex production issues across distributed systems, APIs, networking, and GPU-backed workloads.
• Lead incident reviews and RCAs to turn failure modes into lasting engineering improvements.
• Reduce operational toil through automation, self-healing systems, and deployment safety.
• Collaborate with engineering teams on capacity planning, scaling, and architectural improvements.

Requirements

• Strong experience operating and troubleshooting production systems at scale in an SRE or Platform Engineering role.
• Deep understanding of distributed systems and debugging across applications, databases, queues, and infrastructure.
• Experience designing and operating observability systems using metrics, logs, and distributed tracing.
• Proficiency with Kubernetes, containers, IaC, and automated deployment practices.
• Ability to write software and automation using Python, Go, or PHP.
• Comfortable participating in an engineering on-call rotation and taking ownership of production problems.

Nice to have

• Experience with GPU environments or AI and ML workloads.
• Experience with RabbitMQ or other distributed messaging systems.
• Experience operating MySQL, Redis, or ClickHouse.
• Experience with global traffic management, load balancing, and CDN platforms.

Culture & Benefits

• Remote-first collective with twice-yearly in-person retreats.
• Flexible working hours outside of core collaboration blocks.
• Generous paid time off including vacation, sick days, and public holidays.
• Meaningful stock options to share in company growth.
• Paid family leave for maternity, paternity, and caregiving.
• Emphasis on recharging with downtime after intense release cycles.