Solutions Engineer

About the RoleWe’re looking for a Forward Deployment Engineer (FDE) to work directly with customers and partners to design, deploy, and validate Inference dedicated endpoint & Model-as-a-Service products on GMI’s global infrastructure.This is a high-impact, hybrid engineering role that sits at the intersection of platform engineering, applied ML, and customer success. You’ll be embedded with customers during early-stage deployments—turning research ideas, datasets, and business requirements into working, performant systems on real GPU clusters.If you enjoy being close to users, debugging real systems, and shipping results fast (not just writing docs), this role is for you.What You’ll DoOwn customer POCs end-to-endDeploy and optimize LLM and multi-modal inference workflows on GMI clustersTranslate customer requirements into concrete system designs and experimentsForward-deploy with customersWork hands-on with research teams, startups, and enterprise customersDebug performance, stability, and correctness issues in real environmentsInference deploymentStand up and tune inference stacks (e.g. vLLM / SGLang / Ray Serve–style architectures)Optimize latency, throughput, GPU utilization, and cost efficiencyModel-as-a-Service enablementHelp customers test, evaluate, and adopt the most frontier LLM and multi-modal models through GMI's unified APIGuide model selection, API integration, and migration across providers; shorten the "idea → production" cycleValidate correctness, compatibility, and performance across the MaaS model catalogPerformance & reliabilityDiagnose GPU, networking, and distributed system bottlenecksRun benchmarks, profiling, and stress tests on multi-GPU / multi-node setupsFeedback loop to productFeed real-world customer learnings back into GMI's platform, SDKs, and APIsHelp shape reference architectures, cookbooks, and best practicesWhat We’re Looking ForCore RequirementsProficiency in at least one programming language (Python and Golang preferred)Solid understanding of software systems and distributed systemsHands-on experience with ML inference or serving systemsComfort working directly with customers and ambiguous requirementsAbility to debug end-to-end systems (code, infra, networking, performance)Nice to HaveExperience with:LLM inference frameworks (vLLM, SGLang, Ray Serve, Triton, etc.)Global, distributed systemsHands-on experience developing and maintaining production services on KubernetesGPU performance profiling, optimization, and inference benchmarkingPrior experience as:Forward Deployed EngineerSolutions EngineerML Platform EngineerApplied Research EngineerWhat Makes This Role SpecialYou’re close to real users and real GPUs—not abstract roadmapsYou’ll work on cutting-edge inference and frontier models, not toy demosYou’ll influence product direction through direct customer feedbackFast iteration, high ownership, and visible impactWho Thrives HereEngineers who like shipping over theorizingPeople who enjoy being the “last mile” problem solverBuilders who want exposure to both deep systems and applied MLThose excited by early-stage POCs that turn into real production systems