What is vLLM?

vLLM is an open-source library designed for serving and optimizing the performance of Large Language Models (LLMs) through efficient memory management.

307 open vLLM jobs on Findyet.

Named alongside vLLM

Jobs asking for vLLM

NC
Normal Computing

4 hours ago

Runtime Engineer

NewBe an early applicant North AmericaFull-time
United States

Normal’s hardware runs the most memory-bound parts of large-model inference inside memory itself, rather than shuttling weights to a processor The software that makes this programmable doesn’t exist yet in any standard…

C++ CUDA Firmware FPGA LLM +2 skills
200K – 300K $
Sign in to see your match

Apply
BV
Bright Vision Technologies

5 hours ago

GPU Software Engineer (CUDA)

NewBe an early applicant RemoteNorth AmericaFull-time
United States

Designs and optimizes high-performance CUDA kernels and GPU libraries for AI training, inference, and HPC workloads. Works with ML engineers to profile production GPU systems using Nsight and NCCL, shipping performance improvements in C++/CUDA, PyTorch, JAX, or Triton.

AI Cloud C++ CUDA Distributed Training +8 skills
100K – 175K $
Sign in to see your match

Apply
D
DevBrother

6 hours ago

AI Platform Infrastructure Engineer (Telecom Domain)

NewBe an early applicant RemoteEuropeFull-timeLead

Designs and maintains a secure, on-premise AI platform for a European telecom provider, managing multi-GPU servers, local LLM serving (vLLM/SGLang), RAG/search, STT/TTS, and Ubuntu LTS infrastructure in air-gapped environments, with occasional travel to Croatia for hardware setup.

AI Data Engineering Embeddings Firmware Linux +10 skills

Sign in to see your match

Apply
BV
Bright Vision Technologies

7 hours ago

Model Optimization Engineer

NewBe an early applicant RemoteNorth AmericaFull-time
United States

Bright Vision Technologies is a technology consulting and software development company delivering cloud, AI, data, and enterprise solutions across the United States. This is a fantastic opportunity to join an…

AI Cloud C++ Deep Learning DeepSpeed +11 skills

Sign in to see your match

Apply
BV
Bright Vision Technologies

7 hours ago

ML Systems Engineer

NewBe an early applicant RemoteNorth AmericaFull-time
United States

Designs, builds, and operates reliable ML inference platforms for serving large models in production, handling request routing, batching, caching, autoscaling, GPU utilization, and observability. Core technologies include Python, Go/Rust/C++, Kubernetes, and inference frameworks such as vLLM or TensorRT-LLM.

AI API Cloud C++ Distributed Systems +10 skills
145K – 165K $
Sign in to see your match

Apply
XT
Xperteez Technology

7 hours ago

Member of Technical Staff, Model Training (infra & platform), Remote- Full TIme

NewBe an early applicant RemoteNorth AmericaFull-time
United States

Member of Technical Staff for Model Training infrastructure and platform at Xperteez Technology. The role involves architecting and scaling distributed systems for supervised fine-tuning, reinforcement learning, and distillation across GPU clusters, owning inference optimization, experiment tracking, and platform architecture for AI research teams, using Python and systems languages such as C++, R

AI API Cloud C++ CUDA +16 skills

Sign in to see your match

Apply
M
micro1

7 hours ago

Member of Technical Staff, Model Training (infra & platform)

NewBe an early applicant RemoteNorth AmericaFull-time
United States

Builds and scales distributed GPU infrastructure for large-scale model training (SFT, RL, distillation) and agent execution platforms, optimizing PyTorch/DeepSpeed/Ray pipelines, inference engines (vLLM, TensorRT-LLM), and Kubernetes-orchestrated clusters. Owns architecture from distributed training to experiment tracking and fault recovery.

AI API Cloud C++ CUDA +16 skills
200K – 320K $
Sign in to see your match

Apply
SD
Slash Digital

9 hours ago

Machine Learning Engineer (Audio & LLM Stack)

NewBe an early applicant RemoteNorth America
United States

The Machine Learning Engineer owns the full AI stack for an AI voice-sensing wearable, expanding a speech emotion recognition model into a physics-based harmonic engine and managing a dual-instance vLLM setup on GCP with Llama 3.1 8B and Qwen 2.5 32B, using PyTorch, Python, and audio ML frameworks.

AI API Cloud DevOps FastAPI +11 skills

Sign in to see your match

Apply
N
NVIDIA

10 hours ago

Engineering Manager, Deep Learning Inference

NewBe an early applicant RemoteNorth America
United States

Leads and scales an engineering team building NVIDIA’s deep learning inference software (vLLM, SGLang, FlashInfer) for GPU-accelerated AI model deployment. Drives roadmap, performance optimization, and cross-team collaboration for LLMs and generative AI on NVIDIA GPUs using CUDA, Triton, and NCCL.

Agile AI C++ CUDA Deep Learning +8 skills
184K – 357K $
Sign in to see your match

Apply
JS
John Snow Labs

11 hours ago

Machine Learning Engineer - Large Language Models

NewBe an early applicant Remote

The Machine Learning Engineer trains, tunes, and evaluates large language models for healthcare use cases using techniques such as SFT, PEFT, DPO, PPO, and RAG, collaborating with engineers, data scientists, and medical professionals. Core technologies include PyTorch, Axolotl, vLLM, TGI, and llama-cpp.

AI Data Science Deep Learning DevOps Fine Tuning +10 skills

Sign in to see your match

Apply

See all 307 →