What is SGLang?
SGLang is an open-source inference engine and structured generation runtime for serving large language models at high throughput.
Also written as sg lang.
920 open SGLang jobs on freehire.
Named alongside SGLang
Jobs asking for SGLang
Deliveroo
122 views 3 hours agoSenior Software Engineer, GenAI Platform
Open 20d UKSenior 1 questionUnited KingdomLondon, DeliverooSenior engineer on Deliveroo's GenAI Platform team (part of DoorDash) builds the shared ML infrastructure that lets teams ship GenAI products to production: LLM/Agent gateways, evals, guardrails, and open-weight model serving on GPUs, plus batch inference and fine-tuning. Core stack is Python, distributed systems, and GPU/Kubernetes-based inference platforms.
London, United Kingdom - Deliveroo, Posted 3 hours ago, 1 question Sign in to see your matchAgentic AI AI API Automation AWS +24 skillsПАО Сбербанк
12 views 4 hours agoML-инженер (Online RL) / Post-Training LLM
Open 41d CISRussiaг МоскваМы развиваем GigaChat и ищем сильного ML-инженера в команду online RL. Это роль для человека, который умеет доводить исследовательские идеи до работающих решений: проектировать и запускать эксперименты, строить…
г Москва, Posted 4 hours ago Sign in to see your matchDeepSpeed Distributed Training GPU LLM Machine Learning +5 skillsxai
148 views 4 hours agoSr. Backend Engineer, API
Open 145d UKSenior Salary + equity 7 questionsUnited KingdomLondon, EnglandBuilds and scales a high-throughput AI inference API in Rust, owning model serving, routing, and observability for global developer access.
London, England, United Kingdom, Posted 4 hours ago, 107K – 262K £, Salary + equity, 7 questions Sign in to see your matchAPI Authentication ClickHouse C++ Distributed Systems +11 skills107K – 262K £- 10 hours ago
Sr. Software Engineer, Training/Inference (C++)
New North AmericaSenior Salary + equity 6 questionsUnited StatesPalo Alto, CASenior C++ engineer on xAI's (SpaceXSI) high-performance inference platform serving Grok to millions of users. Day-to-day: building distributed model-serving infrastructure (KV cache, batching, load balancing, auto-scaling) and optimizing latency down to GPU kernels, quantization, and speculative decoding.
Palo Alto, CA, Posted 10 hours ago, 220K – 357K $, Salary + equity, 6 questions Sign in to see your matchCI/CD C++ GPU LLM Quantization +5 skills220K – 357K $ - 105 views 10 hours ago
Software Engineer, Training/Inference (C++)
Open 145d North America Salary + equity 7 questionsUnited StatesPalo Alto, CA, Seattle, WABuilds and optimizes high-performance AI inference systems in C++ to serve millions of users with low latency and high reliability, using GPU engines like vLLM and Triton.
Palo Alto, CA; Seattle, WA, Posted 10 hours ago, 180K – 440K $, Salary + equity, 7 questions Sign in to see your matchCI/CD C++ GPU LLM Quantization +5 skills180K – 440K $ Alibaba Group
10 hours ago阿里云智能-计算虚拟化研发专家-北京/杭州
New APACChinaBeijing, HangzhouR&D expert on Alibaba Cloud's edge-cloud Hypervisor team, building virtualization and sandbox products (secure containers, AI Agent sandboxes), live migration/hot-upgrade and DPU offload, plus edge-AI infrastructure like GPU cluster monitoring and inference acceleration. Core stack: C/C++ (plus Go/Python/Rust), Linux kernel, KVM/QEMU, x86/ARM, GPUs.
Beijing; Hangzhou, Posted 10 hours ago Sign in to see your matchAI Cloud C++ CUDA GPU +7 skillsRicursive Intelligence
14 hours agoMember of Technical Staff, Post-Training
New On-siteNorth AmericaFull-time 2 questionsUnited StatesPalo AltoRicursive Intelligence is a frontier AI lab building self-improving systems, starting with chip design. We are reinventing chip development and closing the loop between AI and the hardware that fuels it, recursively…
Palo Alto, Posted 14 hours ago, 2 questions Sign in to see your matchAgentic AI AI Anthropic Data Pipelines Distributed Training +6 skillsScale AI
54 views 16 hours agoStaff Software Engineer, RL Environments
Open 64d North AmericaFull-timeStaff Salary + equity 3 questions Licensed UK sponsor — This employer appears on the GOV.UK register of licensed sponsors for the Skilled Worker and related work routes. The licence belongs to the employer and is not a commitment to sponsor this role.United StatesSan Francisco, CA, New York, NYStaff-level hands-on engineer who owns the platform and hard engineering behind Scale's RL environments for LLM training: sandboxed execution, packaging, rollout orchestration, trajectory capture, and trustworthy verifiers/graders. Core stack is Python plus another systems language, Docker/Kubernetes/gVisor/Firecracker, distributed backend systems, and LLM agent tooling.
San Francisco, CA; New York, NY, Posted 16 hours ago, 252K – 315K $, Salary + equity, 3 questions Sign in to see your matchAgentic AI AI AWS Azure CI/CD +20 skills252K – 315K $SambaNova Systems
116 views 17 hours agoPrincipal Cloud Platform Engineer
Open 90d North AmericaFull-timePrincipal Salary + equity No extra questions Licensed UK sponsor — This employer appears on the GOV.UK register of licensed sponsors for the Skilled Worker and related work routes. The licence belongs to the employer and is not a commitment to sponsor this role.H-1B sponsor history — This employer has had H-1B petitions approved by USCIS in the last five fiscal years, per the USCIS H-1B Employer Data Hub. The approval belongs to the employer and is not a commitment to sponsor this role.United StatesAustin, Texas, San Jose, CaliforniaBuild and maintain the cloud infrastructure that powers SambaNova’s AI inferencing service, ensuring high availability, low latency, and scalable performance across regions.
Austin, Texas, United States; San Jose, California, United States, Posted 17 hours ago, Salary + equity, No extra questions Sign in to see your matchAgentic AI AI Ansible Argo CD AWS +33 skills