Jobs Referso Partner API

Free job alerts

LLM inference optimization jobs

Job titleLocation

Popular:United States Canada Viet Nam

All filtersRefine by skill, company, date, job type, industry and more

Company

Skillsjobs that use all of them

LLM inference optimization

Popular

Date posted

Any timePast hourPast 24 hoursPast week

Workplace

RemoteHybridOn-site

Job type

Full-timePart-timeContractInternshipTemporary

Experienceyears required

0–2 years2–5 years5–10 years10+ years

Salary

Salary listed

Education

High schoolAssociate degreeBachelor's degreeProfessional certificatePostgraduate degree

Industryfield of work

Software & InternetHardware & ElectronicsEngineeringHealthcareLife Sciences & ResearchFinance & AccountingSales & Business DevelopmentMarketing & CommunicationsCreative & DesignCustomer Service & SupportAdministrative & OfficeHuman Resources & RecruitingLegal & ComplianceManagement & OperationsEducation & TrainingRetailHospitality & Food ServiceManufacturing & ProductionSkilled Trades & ConstructionTransportation & LogisticsFacilities, Cleaning & SecuritySocial Services & Public SectorEnergy, Environment & Agriculture

1 selected

Skill:LLM inference optimization

Referso Jobs

Fresh jobs from employer career sites in the US and Europe. Search free, get alerts free, and let Referso apply when you're ready.

Job seekersSearch jobs Free job alerts Remote jobs Jobs by location Jobs by skill

RefersoAuto-apply How it works Pricing Log in

For companiesPartner API (beta)API docs Contact sales

CompanyAbout Contact Privacy Terms

© 2026 Referso. Jobs link to the original posting; Referso is not affiliated with the employers listed.Privacy Terms Request a removal

1–1 jobs· newest first

AI Software Development EngineerNew
Advanced Micro Devices, Inc · Seoul, Korea

+10K new in the last hour

AI Software Development Engineer

Advanced Micro Devices, Inc · Posted Nov 11, 2026

Seoul, Korea

Apply with RefersoAI Apply on careers page

Software engineer to build AI routing and serving stack for AMD's vllm-sr.

Responsibilities

Build routing intelligence for vllm-sr
Make vllm-sr simple to deploy and operate
Build vllm-sr into a universal serving engine
Optimize decision model inference
Train foundation decision models

Requirements

Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or related field

Skills

Python Go Rust C++large language models vLLM SGLang PyTorch Hugging Face Envoy

GPU programming (HIP, CUDA, Triton)

LLM inference optimization

training or post-training models

technical writing

public speaking

community building

See full job description