caferemote
Zenlayer

Staff Software Engineer, LLM Inference Platform

Remote United States Full-time Lead $300K – $600K / year Posted 4 days ago
Apply now
Work from
United States
Contract
Full-time
Experience
Lead
Salary
$300K – $600K / year
Posted
16 November 2026
Apply by
15 January 2027

As the technical lead for inference performance, you will own end-to-end responsibility for the platform's Token Performance. For models ranging from hundreds of billions to trillions of parameters (including MoE), you will continuously reduce cost per million tokens and increase per-GPU Goodput while meeting TTFT/TPOT SLOs, and prove the gain from every optimization with reproducible data.

About Zenlayer

Zenlayer is the first massively distributed edge cloud provider, operating 290+ Points of Presence across 70+ countries. With accolades including PTC “Best Networking Innovation”, “Outstanding Cloud, Data Center, or Interconnection Company”, and Inc. 5000, we enable businesses to deploy and run applications at the edge, thus reducing network latency to the end user. Zenlayer focuses on improving connections worldwide, all while nurturing a unique company culture that values service, growth, and trust. As a “Zenplayer”, you’ll be joining a community of success-driven team players that share the dream of powering a better-connected world.

Responsibilities

1. End-to-End Performance Attribution and Benchmarking

  • Establish a unified Token Performance metrics framework (TTFT, TPOT, Goodput, GPU utilization, per-token cost), and build load-testing benchmarks that reflect real production traffic (high concurrency, long context, multi-turn Agent workloads)
  • Perform bottleneck attribution for models such as DeepSeek, Kimi, GLM, Qwen, and MiniMax across compute, memory bandwidth, communication, scheduling, and queuing, and let the data determine which layer is the dominant constraint

2. Kernel-Level Inference Engine Optimization

  • Dive deep into the source code of vLLM / SGLang / TensorRT-LLM, customizing and contributing upstream on critical paths such as the scheduler, Continuous Batching, Chunked Prefill, CUDA Graph, and KV block management
  • Clearly define the responsibility boundary between the inference engine and orchestration layers such as Dynamo / llm-d, and reduce tail latency through request routing and load balancing

3. PD Disaggregation and KV Cache Transfer

  • Lead the core design of Prefill-Decode disaggregation: the KV transfer path (NIXL/RDMA/UCX), transfer-compute overlap, and phase-aware autoscaling
  • Define the failure domains and recovery semantics of cross-instance KV transfer, and answer the key question: under which workloads does PD disaggregation deliver gains, and under which does it make things slower

4. MoE Parallelism and Wide-EP

  • Design hybrid TP/PP/DP/EP parallelism strategies and quantify the trade-offs between EP and TP
  • Tackle expert load imbalance and All-to-All communication overhead, and drive Wide-EP into production

5. Kernels and Quantization

  • Write and tune critical CUDA (and ROCm/HIP) operators: memory access optimization, kernel fusion, and Attention / MoE / communication-related kernels
  • Build a closed-loop "quantization – accuracy – throughput" evaluation: the real-world gains and accuracy regressions of FP8/FP4/INT4/AWQ/GPTQ across different engines and hardware

Requirements

  • First-principles understanding of Transformer inference: the compute vs. memory-bound nature of Prefill and Decode, the KV Cache memory model, the differences among MHA/GQA/MLA, and how MoE routing constrains parallelism
  • Source-level, in-depth experience with at least one mainstream inference engine, with real cases of identifying and fixing bottlenecks in scheduling, kernel selection, or KV management
  • CUDA kernel tuning skills (Nsight profiling, memory optimization, fusion, CUDA Graph) with hands-on practical experience
  • Bachelor’s degree in Computer Science, Electrical/Computer Engineering, or related field (HPC systems, ML Systems).
  • Minimum 6 years in systems/Performance Engineering, with at least 2-3 years directly on LLM or GPU performance work

Preferred, but not required

  • Experience with Merged PRs in vLLM
  • Experience operating at cluster sale (hundreds to thousands of GPUs)

Salary

$300,000-600,000 DOE

Discussion

No comments yet. Ask a question or share a tip about this role.

Apply now

Similar remote jobs

Browse all →

NEN SMIT Senior Solution Architect

Leidos
Remote United States Full-time $107K – $195K / year

Leidos is currently seeking a Senior Solution Architect to join our SMIT Growth Team. The Senior Solution Architect will be responsible for providing technical leadership and delivering…

1h ago DevOps and Sysadmin

Cloud Architecture Manager

Smart Tech Contracting
Remote United States Full-time $140K – $170K / year

Smart Tech Contracting delivers turnkey BAS & EPMS solutions for mission-critical colocation and hyperscale data centers operating at national program scale. As a Master Systems Integrator…

1h ago DevOps and Sysadmin

Cloud System Administrator (Shift B - Day)

NexusTek
Remote United States Full-time $28 – $31 / hour

Shift Schedule: This is a 12-hour day shift (5:45 AM to 6:15 PM Mountain Time), operating on a 12/7 rotational schedule . The rotation is as follows: Week 1: Work Thursday through Saturday…

2h ago DevOps and Sysadmin

Principal, Software Development

Common Securitization Solutions
Remote United States Full-time $181K – $208K / year

OVERVIEW The Company U.S. Financial Technology (U.S. FinTech) is seeking an experienced Principal, Software Development to join our team of talented professionals. This is a full-time…

4h ago DevOps and Sysadmin

Lead Devops Engineer

Way2B1
Remote United States Full-time

Our Company and the Role This is a hands-on Lead DevOps Engineer role responsible for designing, operating, and evolving a highly available, multi-tenant platform on AWS. You will work…

4h ago DevOps and Sysadmin

Senior Platform Engineer — Kubernetes, DevOps, & Cloud Infra (US)

Genios AI
Remote United States Full-time

We are on a mission to build the AI-native platform for finance —a multi-agent system that reimagines how investment teams make decisions and empowers them to move faster, think deeper,…

4h ago DevOps and Sysadmin

Get remote jobs the moment they are posted

Choose your categories and skills. We push matching jobs to your device. No email, ever.