Teams at StackYak

Owns end-to-end production networking for customer connectivity to GPU workloads, spanning Linux hosts, data-center fabrics, carriers, cloud, routing, segmentation, tenant isolation, secure tunnels, observability, and incident response. The role combines architecture, implementation, debugging, automation, and production ownership. The engineer will use Python and Terraform to productize repeatable connectivity patterns and collaborate on RDMA, multi-node GPU traffic, topology, and performance.

Own production inference for large language models across single and multi-node GPU systems. Select and tune precision, quantization, parallelism, memory strategies, batching, concurrency, topology, and serving runtimes. Benchmark and validate latency, throughput, utilization, and cost; operate model lifecycles and resolve incidents across runtimes, GPUs, hosts, drivers, and networks. Build software that automates deployment decisions and captures inference expertise for reliable multi-tenant and dedicated serving.

Own and evolve StackYak’s backend control plane, including PostgreSQL data models, durable workflows, APIs, identity and authorization, infrastructure integrations, billing, and production reliability. Build programmatic access through management APIs, Terraform, CLI, and agent interfaces. Design systems for correctness, idempotency, tenancy, security, and partial failure while operating the platform in production and shaping its technical standards.