MLE (LLM inference)
About US
GMI Cloud is a fast-growing AI infrastructure company backed by Headline VC and one of only six cloud providers worldwide to earn NVIDIA’s prestigious Reference Platform Cloud Partner designation . We operate 8 of our own GPU clusters across the U.S. and Asia, delivering a full spectrum of services from GPU compute service to AI model inference API solutions. As an NVIDIA Reference Platform Cloud Partner, our infrastructure meets the highest standards for performance, security, and scalability in AI deployments. We empower AI startups and enterprises to “build AI without limits,” providing everything they need to prototype, train, and deploy AI models quickly and reliably.
About this role
We are hiring a Machine Learning Engineer, LLM Optimization to build a world-leading inference optimization team and make GMI Cloud the industry benchmark for LLM serving performance.
This role is for engineers who want to work at the frontier of AI systems. You will drive the research, validation, and productionization of the most advanced inference optimization techniques, and turn them into real competitive advantage across GMI’s inference platform.
Our goal is to make GMI the company that leads the industry in how fast we discover, evaluate, combine, and operationalize the best optimization strategies for real customer workloads. That means not only adopting the latest advances, but also defining best practices, developing our own optimization methodologies, and building the internal framework that keeps GMI ahead of the curve.
You will focus on B200-first optimization, with support for H200 evolution, across core domains including quantization, speculative decoding, KV cache and memory management, prefill/decode disaggregation, and system-level inference optimization. You will work closely with platform and infrastructure teams to transform cutting-edge ideas into measurable gains in latency, throughput, cost efficiency, and production scalability.
Key Responsibilities
- Drive frontier research and engineering in LLM inference optimization, building GMI’s industry-leading capabilities in performance, efficiency, and scalability.
- Develop next-generation optimization strategies for large-scale LLM serving across model execution, runtime systems, and production inference platforms.
- Advance state-of-the-art techniques in quantization and precision optimization to improve throughput, latency, memory efficiency, and cost-performance across modern GPU systems.
- Push the frontier of speculative decoding and related acceleration methods, including both systems and model-level approaches for faster generation.
- Lead innovation in KV cache and memory optimization, improving long-context serving efficiency, memory utilization, and multi-tenant performance.
- Develop advanced architectures for prefill/decode disaggregation and other distributed inference optimization strategies for large-scale production environments.
- Drive system-level optimization across scheduling, batching, routing, gateway orchestration, adapter serving, and end-to-end inference efficiency.
- Build scalable optimization frameworks, performance methodologies, and engineering practices that allow GMI to stay ahead of the industry as models, hardware, and serving patterns evolve.
- Turn cutting-edge optimization ideas into production-ready capabilities that improve real-world customer workloads across latency, throughput, quality, and cost.
- Collaborate closely with platform, infrastructure, and product teams to make inference optimization a core technical advantage of GMI Cloud.
Required Skills
- Strong hands-on experience with LLM inference systems and performance optimization.
- Solid understanding of inference metrics and tradeoffs, including TTFT, ITL, throughput, goodput, tail latency, GPU utilization, memory efficiency, and quality/cost tradeoffs.
- Experience with one or more modern serving stacks such as SGLang, vLLM, TensorRT-LLM, Triton, or similar systems.
- Deep familiarity with GPU-based inference, model serving architecture, and production bottlenecks around compute, memory bandwidth, KV-cache behavior, and scheduling.
- Strong experimentation skills: able to design benchmarks, interpret results, debug regressions, and produce actionable conclusions rather than isolated microbenchmark wins.
- Comfortable working across research-style validation and production engineering, with a bias toward measurable impact in real customer scenarios.
- Strong coding and systems skills in Python, with practical experience in profiling, observability, and performance debugging.
- Clear communication skills and the ability to explain technical tradeoffs to both engineers and cross-functional stakeholders.
Preferred Qualifications
- 1+ years of hands-on experience in LLM inference optimization, ML systems optimization, or closely related areas.
- Experience working on optimization for large-scale model serving, such as latency reduction, throughput improvement, memory efficiency, or cost-performance tuning.
- Familiarity with one or more major areas of inference optimization, including quantization, speculative decoding, KV cache optimization, prefill/decode disaggregation, or system-level serving optimization.
- Experience with modern LLM serving stacks, GPU inference systems, or production ML infrastructure is a strong plus.
