Tech jobs
Job listings
AI / LLM Inference Engineer
Engineer AI/LLM inference on GPU clusters: benchmark, tune, and optimize model serving with vLLM, Triton, or TensorRT-LLM to hit latency, throughput, and memory targets.
Staff ML - GenAI Engineer, Voice & Speech
Build and lead ML infrastructure for voice/GenAI at scale, enabling teams to ship AI-powered features while democratizing ML tooling for developers.
AI/ML Architect
Design and deploy scalable, real-time AI systems including LLM inference pipelines, RAG, and vector databases using Python, TensorFlow/PyTorch, and Kubernetes.
Machine Learning Ops Engineer
Build and deploy LLM-powered tools, RAG systems, and agentic workflows for autonomous aircraft systems, focusing on retrieval quality, tool integrations, and production-grade AI infrastructure on Kubernetes.
大模型推理工程师
推理服务部署与优化：负责大语言模型、多模态模型在生产环境中的推理部署与性能优化，基于 vLLM、SGLang、TensorRT-LLM 等主流推理框架，建设并优化推理服务能力； 推理链路性能调优：负责模型推理全链路优化，包括推理加速、批处理调度、KV Cache 优化等，持续提升吞吐、降低延迟、减少 GPU 资源成本；系统性降低硬件延迟瓶颈，保障高并发下线上服务稳定性；…
Senior Product Manager - AI Platform Inference
Lead product strategy for NVIDIA’s AI inference tools and SDKs, collaborating with developers to optimize GenAI deployments on GPUs.
Engineering Manager, Deep Learning Inference
Lead a team building and optimizing NVIDIA’s deep learning inference frameworks (e.g., vLLM/SGLang) to deploy LLMs and generative AI efficiently on GPUs, using CUDA, Triton, and multi-GPU stacks.
Machine Learning Engineer - Voice Conversion
Build and ship state-of-the-art voice conversion and speech models end-to-end, from data curation to production inference, using large-scale diffusion/flow-matching transformers and PyTorch.
Engineering Manager - AI Product(100% Remote EMEA)
Location: Remote (Europe Time Zone) Start date: ASAP Language: English Team: AI About the Role Our client is a European technology company operating a cloud and infrastructure platform, and we are looking for an AI…
Senior Python Software Developer
Senior Python developer builds and integrates AI/ML services for a global vehicle-claims platform, using FastAPI, AWS ML, and DevOps tooling.