Back End Developer

Backend Engineer (APIs, Load Balancing & Scheduling)

Full-Time | Remote or Hybrid | High-Impact Role

The Opportunity

They are building transformative AI solutions powered by high-performance infrastructure. As a Backend Engineer, you will architect the critical API layer, intelligent load balancers, and workload schedulers that manage their global GPU fleet.

What You’ll Do

• Core Systems & Load Balancing: Build REST/GraphQL APIs and gateways for model inference and resource management. Develop smart load balancers that distribute requests based on latency, cost, and GPU availability.
• LLM Orchestration: Implement token streaming, request queuing, and batching for massive-scale inference workloads.
• Intelligent Scheduling: Design GPU resource allocators using bin-packing algorithms that optimize for hardware topology (NVLink, PCIe, NUMA).
• Reliability & Scale: Implement preemption, checkpointing, and multi-tenant isolation. Build observability stacks (Prometheus, OpenTelemetry) to monitor SLOs for throughput and latency.

What They’re Looking For

• Experience: 4–7+ years in backend/distributed systems or infrastructure engineering.
• Languages: Strong proficiency in Go, Python, or Rust; deep experience in API design (REST/GraphQL).
• Distributed Systems: Proven expertise in service discovery, failover, message queues, and microservices.
• Cloud & K8s: Solid production experience with AWS/GCP/Azure, Kubernetes, and Docker.
• Networking: Strong fundamentals in TCP/IP, DNS, TLS, and HTTP.

Nice-to-Have

• Experience with GPU-accelerated workloads or HPC scheduling.
• Familiarity with LLM frameworks (vLLM, TensorRT-LLM) or K8s internals.
• Experience with API gateways (Kong, NGINX) or service meshes (Istio).
• Background in high-throughput systems (100k+ req/sec).

If this role is of interest to you or anyone you know, please apply within.