vLLM
Open-source inference server for language models.
Also counted under Open / local models.
59
Open engineering roles mention it
12
Of those, leadership roles
39
Companies
Show as table
| Week | postings |
|---|---|
| 24 Aug - 30 Aug 2026 | 3 |
| 31 Aug - 6 Sept 2026 | 0 |
| 7 Sept - 13 Sept 2026 | 1 |
| 14 Sept - 20 Sept 2026 | 5 |
| 21 Sept - 27 Sept 2026 | 2 |
| 28 Sept - 4 Oct 2026 | 2 |
| 5 Oct - 11 Oct 2026 | 4 |
| 12 Oct - 18 Oct 2026 | 2 |
| 19 Oct - 25 Oct 2026 | 1 |
| 26 Oct - 1 Nov 2026 | 3 |
| 2 Nov - 8 Nov 2026 | 6 |
| 9 Nov - 15 Nov 2026 (so far) | 2 |
Companies
Open postings (59)
Deliveroo · London, United Kingdom - Deliveroo
Software (general)United KingdomCursorClaude CodeOpenAI CodexvLLMLocal / open-weight LLMsQwen+10 more…cases into reusable platform capabilities Proficiency in using AI coding tools (e.g., Claude Code, Codex, Cursor) in the full software development lifecycle, including designing, generating code, testing, monitoring and…
Snowflake · US-WA-Bellevue; US-CA-Menlo Park (United States)
…effective execution strategies, and adapting system configurations with minimal manual tuning. We embrace AI-native engineering, using AI not only as the workload we optimize, but also as a tool to accelerate system development,…
KRAFTON · Seoul; Seoul, South Korea; Seoul
…등 클라우드 환경에서 서비스를 개발하거나 운영해본 경험이 있으면 더욱 좋습니다 AI Native 개발 역량 Claude Code, OpenAI Codex, Google Antigravity, Cursor 등 AI 코딩 도구를 개발 과정에서 적극적으로 활용하고 있는 분 AI 코딩 도구의 결과물을 그대로 사용하는 것이 아니라, 직접 검토하고 수정하며 개발할 수 있는 분 새로운 AI 개발 도구와 개발…
Isomorphiclabs · London; London, England, United Kingdom
Data / ML engineeringUnited KingdomvLLMLocal / open-weight LLMsAgentic codingAgentic workflowsEvals / LLM evaluationMCP (Model Context Protocol)+2 more…evals for different tasks. Agentic Tooling: Develop the internal frameworks and IDE integrations to leverage agentic coding and agentic workflows at scale. Contribute to shaping best practices and providing a great user…
KRAFTON · Seoul
…수 있는 분 운영 과정에서 확인한 문제를 구조적 개선 과제로 연결하고, 우선순위와 실행 방안을 제시할 수 있는 분 AI Native 개발 역량 Claude Code, OpenAI Codex, Cursor 등 코딩 에이전트를 일상적인 개발 도구로 활용 하고, 각 도구의 강점과 한계를 고려해 업무에 적용할 수 있는 분 CLAUDE.md, AGENTS.md, Rules 등 프로젝트 컨텍스트를 설계해…
OpenAI · San Francisco; Seattle (United States)
…evaluation harnesses, or artifact pipelines. - Experience with automated optimization, search systems, coding agents, or evaluator-driven systems that iteratively improve kernels or runtime configurations. About…
Siili · Helsinki, Finland; Joensuu, Finland; Jyväskylä, Finland; Kuopio, Finland; Oulu, Finland; Seinäjoki, Finland; Tampere, Finland
Data / ML engineeringFinlandCursorClaude CodeGitHub CopilotOpenAI CodexClaudeChatGPT / GPT models+14 more…Azure, AWS, GCP Python Vector databases, e.g. Pinecone, pgvector AI powered development tools: ChatGPT, Cursor, GitHub Copilot, Claude Code, OpenAI Codex What we offer A technically strong and collaborative community:…
Multiversecomputing · Donostia, Spain
…machine learning and data analytics solutions. Autoscaling (KEDA, Karpenter) and GPU/LLM inference serving (vLLM, SkyPilot, RunAI). Internal developer platforms (Backstage) and IAM / least-privilege…
Datadog · Paris, France; Paris, Paris, France
…such as Megatron-LM, TorchTitan, or DeepSpeed You have experience with LLM inference engines such as vLLM or SGLang, including batching and KV-cache management You have experience with RL training systems and…
Xai · Palo Alto, CA; Seattle, WA
…with large-scale, high-concurrent production serving Experience with GPU inference engines (e.g., vLLM, SGLang, Triton, TensorRT-LLM) Strong background in system optimizations: batching, caching, load balancing,…
SopraSteria1 · bundesweit, Germany
DevOps / SRE / PlatformGermanyGermanHugging FacevLLMLocal / open-weight LLMsLangChainFine-tuning / LoRA / PEFT…Kenntnisse und Erfahrung mit relevanten Tools und Frameworks für den ML- und GenAI-Lifecycle, wie Hugging Face, NVIDIA AI Enterprise, vLLM und LangChain, sowie Techniken für Training, Fine-Tuning (z. B. LoRA,…
Multiversecomputing · Barcelona, Spain
Data / ML engineeringSpainHugging FacevLLMLocal / open-weight LLMsAI / agent harnessEvals / LLM evaluation…at top venues (NeurIPS, ICML, ICLR, ACL, etc.), notable open-source contributions, or models released on Hugging Face. Fluency in Spanish. Perks and Benefits Indefinite contract. Equal pay guaranteed. Variable performance…
ALTEN · Boulogne-Billancourt, IDF, France
…time-slicing), dimensionnement des capacités. Expérience de la mise à disposition de LLM en production (vLLM, Triton, KServe ou OpenShift AI). Expérience en air-gapped environments : private registries (Harbor,…
PhysicsX · London; London, England, United Kingdom
…according to the needs of each workload. You will set the technical direction for inference engines such as vLLM and SGLang, and serving platforms such as KServe. You will build foundations that product, delivery and…
Doctolib · Berlin (Germany)
…RAG systems, or reinforcement learning - You are expert in Python, PyTorch/Transformers for training, and vLLM for inference with a track record deploying ML systems in production (AWS/GCP) - You have a PhD in Computer…
Philo · San Francisco; Brooklyn; Cambridge; Remote (United States)
Data / ML engineeringUnited KingdomRemoteOpenAIAnthropicAmazon BedrockvLLMLiteLLMAI / agent harness+6 more…models. - Experience with LLMOps: inference gateways/routers (e.g. LiteLLM), hosted model APIs (Bedrock, OpenAI, Anthropic), RAG pipelines, vector databases (e.g. pgvector, Pinecone, Weaviate), and prompt/version…
Cohere · United States
Software (general)vLLM…live performance. • Hands-on experience with modern inference engines and optimization stacks (e.g., vLLM, TensorRT-LLM, lmd, or Dynamo). • Familiarity with distributed serving techniques, such as prefill/decode…
Perplexity · San Francisco; Remote (United States); Toronto; Seattle; New York City
…the path forward isn't laid out for you. ADDITIONAL EXPERIENCE WE VALUE - Inference serving stacks: vLLM, SGLang, or TensorRT-LLM. - Slurm or other HPC schedulers. - GPU kernel work in CUDA or Triton — not…
Mistral AI · Paris; London (France)
…quality loss. - Collaborate with the Inference Foundation team to integrate validated techniques into the vLLM-based serving stack. - Partner with pretraining and RL teams when techniques require co-training,…
Doctolib · Paris (France)
DevOps / SRE / PlatformFranceRemoteAmazon BedrockVertex AIAzure OpenAIvLLMLLM observabilityLiteLLM+6 more…metering, cost attribution, guardrails, reserved-capacity pooling (Azure OpenAI PTUs, Vertex AI GSUs, AWS Bedrock Provisioned Throughput) - Experiment tracking & model registry: MLflow - LLM evaluation & observability:…
Devoteam · Levallois-Perret, IDF, France
Data / ML engineeringFranceFrenchAmazon BedrockVertex AIAzure OpenAIAmazon SageMakervLLMLangChain+9 more…Qdrant, Chroma). Cloud Providers : Solide expérience sur au moins un Cloud majoritaire (AWS SageMaker / Bedrock, GCP Vertex AI, Azure Machine Learning / Azure OpenAI). Conteneurisation & Orchestration : Docker, Kubernetes…
Mistral AI · Paris (France)
…or maintaining evaluation harnesses or benchmarks. - Hands-on experience with inference engines such as vLLM or SGLang. - Experience with agentic or RL environments. - Statistics for experimentation: variance…
Prosus · Amsterdam (Netherlands)
Data / ML engineeringNetherlandsOpenAIAnthropicHugging FacevLLMAgentic workflowsFine-tuning / LoRA / PEFT+1 more…- State-of-the-art infrastructure: H200 GPU fleet, massive proprietary datasets, access to frontier models (OpenAI, Anthropic, Google, Together.ai http://Together.ai) for evaluation and baselines - Expert colleagues who…
Mistral AI · Munich; Warsaw; London (Germany)
…at scale, with clear latency and availability targets - Hands-on experience with inference engines such as vLLM, SGLang, TensorRT-LLM, or others - A solid grasp of inference internals: prefill vs. decode, KV-cache…
CEiiA · Matosinhos, Porto, Portugal
Data / ML engineeringPortugalPortuguesevLLMEvals / LLM evaluationRAGFine-tuning / LoRA / PEFTEmbeddingsLLMOps / MLOps…usar frontier vs open-source vs fine-tuned, com trade-offs claros; Infraestrutura AI: GPUs, model serving (vLLM, TGI ou equivalente), inference pipelines, compute cloud vs on-prem; Integração de dados de múltiplas…
Nscaleoperationsukltd · Houston; New York; San Francisco; Seattle; Houston; New York; San Francisco; Seattle
…AI infrastructure team Maintainer or core contributor to a foundational inference, kernel, or RL framework (vLLM, SGLang, TensorRT-LLM, LMCache, FlashInfer, Triton, verl, OpenRLHF, TRL, DeepSpeed, Megatron-LM,…
Devoteam · Levallois Perret, Île-de-France, France
…Performance (High-Throughput Inference) Déployer, optimiser et opérer les moteurs d'inférence de pointe : vLLM (PagedAttention, Prefix Caching, continuous batching), LLMD, LiteLLM Proxy, SGLang, TGI et Triton Inference…
Snowflake · US-WA-Bellevue (United States)
…production. - Familiarity with GPU and LLM infrastructure — e.g., PyTorch, DeepSpeed/FSDP, Ray, CUDA/NCCL, vLLM; able to debug across the data, infrastructure, and GPU layers. - Demonstrated ability to harden complex…
Mai Group · Remote; München; Paderborn; Köln; Wien; Hamburg; Berlin
Data / ML engineeringGermanyRemoteGermanvLLMOllamaLangGraphLLM observabilityEvals / LLM evaluationRAG+4 more…pgvector, Qdrant oder Neo4j Kubernetes sowie Erfahrung mit selbst betriebenen LLMs und Inferenz-Stacks wie vLLM oder Ollama Erfahrung mit Werkzeugen für LLM-Evaluation und Observability, beispielsweise Langfuse Erfahrung…
Nscaleoperationsukltd · Houston; New York; San Francisco; Seattle; Houston; New York; San Francisco; Seattle
…and sharing infrastructure between inference and training Serving platform and APIs: serving engines (vLLM, SGLang, TensorRT-LLM), model onboarding, and OpenAI-compatible APIs that other engineers and customers build…