AI Infrastructure Architect

Company

hirify.global develops NR-NEXUS, a next-generation AI inference platform.

What you will do

• Lead the software architecture and technical roadmap for NR-NEXUS.
• Write system specifications and translate technical capabilities into product value.
• Research AI infrastructure, SaaS platforms, model serving, and inference trends.
• Define performance goals and lead profiling, benchmarking, and optimization for GenAI and distributed AI workloads.
• Collaborate with engineering teams, customers, partners, and open-source communities on performance, compatibility, and adoption.
• Mentor software engineers and provide technical leadership.

Requirements

• 7+ years of software engineering experience, including 3+ years in software architecture or technical leadership.
• Strong experience with Kubernetes-based platforms, cloud-native architecture, distributed systems, microservices, APIs, and automation.
• Deep understanding of GenAI/LLM infrastructure and distributed workloads.
• Experience designing management software or SaaS platforms for production systems.
• Hands-on experience with observability, including monitoring, logging, alerting, and SLA/SLO tracking.
• Experience with CI/CD, deployment automation, upgrades, rollback mechanisms, security, authentication, authorization, and customer data center integrations.

Nice to have

• Experience with production AI inference clusters using GPUs, AI accelerators, or specialized compute infrastructure.
• Knowledge of model-serving frameworks such as vLLM, Triton Inference Server, or TensorRT-LLM.
• Experience with scheduling, load balancing, autoscaling, failover, cluster observability, and GPU/accelerator orchestration.
• Familiarity with GPUDirect RDMA, NCCL, NVLink, UALink, Prometheus, Grafana, OpenTelemetry, Helm, Argo CD, Istio, KServe, or Kubeflow.
• Experience deploying software in on-premises, edge, private-cloud, or hybrid environments.

Culture & Benefits

• Work closely with engineering teams, customers, partners, and open-source communities.
• Provide technical leadership and mentorship to software engineers.
• Contribute to a next-generation AI inference platform and its ecosystem compatibility.