Staff MaaS Backend Engineer (AI)

Location: Remote within San Jose, CA or Austin, TX

Company

hirify.global is a technology company building Bitcoin mining infrastructure and AI computational infrastructure, including data centers and cloud capabilities for high-demand AI workloads.

What you will do

• Co-own the MaaS system architecture with the Principal Architect and deliver incremental, reversible platform improvements.
• Own Go services and inference APIs supporting OpenAI and Anthropic compatibility, streaming, tool calling, structured output, versioning, routing, circuit breaking, and fallbacks.
• Optimize token throughput, KV and prefix caching, time-to-first-token latency, model serving, LoRA multiplexing, and cold-start-aware autoscaling across Kubernetes GPU fleets.
• Design globally distributed regional inference pools, active-active control planes, capacity-aware failover, load shedding, SLOs, on-call runbooks, and peak-concurrency testing.
• Build secure multi-tenant authorization, identity, API key and OAuth credential lifecycle management, distributed quotas, rate limits, abuse controls, and zero-retention data paths.
• Deliver exactly-once token metering, usage ledgers, billing reconciliation, safe stateful migrations, shadow traffic, dual writes, 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 hands-on experience with Go-based services, production Kubernetes, Envoy, GPU-aware scheduling, PostgreSQL, Redis, and Kafka.
• Experience scaling distributed systems through multi-region active-active deployments, caching, backpressure, performance engineering, and zero-downtime brownfield migrations.
• Strong understanding of LLM serving, server-sent-event streaming, KV and prefix caching, TTFT, throughput, and model-serving trade-offs.
• Experience building reliable metering and billing systems that reconcile high-volume events under partial failure conditions.
• Ability to own observability, SLOs, on-call responsibilities, incident reviews, fail-closed authorization, and strict cross-tenant isolation.

Culture & Benefits

• Full-time employment on a revenue-bearing AI infrastructure platform.
• Direct collaboration with the Principal Architect and ownership of backend engineering standards.
• Responsibility for production reliability, measurable service objectives, and operational improvements.
• Work on infrastructure supporting AI computation and Bitcoin mining operations across multiple countries.