Point your AI agent at freehire and let it find you a job. A CLI and an MCP server over the whole job API — no browser.
Lead a team building and optimizing NVIDIA’s open-source deep learning inference frameworks (e.g., SGLang, vLLM) to deploy LLMs and generative AI efficiently on GPUs from datacenter to edge.
Build and scale the inference infrastructure for generative audio models (TTS, voice conversion, ASR) using Kubernetes, ensuring low-latency, reliable, and scalable model serving for streaming and batch workloads.
Build and optimize AI models for robotics and computer vision, deploying them on edge devices for autonomous systems in defense and commercial sectors using PyTorch/TensorFlow and C++.
The AI Systems Architect will play a critical role in shaping how Optalysys technology is applied to real-world AI workloads. Working across Engineering, Product and Commercial teams, you will help create the…
Solutions Engineer at Ultralytics builds and deploys production-ready computer vision systems using YOLO models, guiding customers from discovery to deployment while collaborating with cross-functional teams.
Research Engineer builds and deploys generative-AI and computer-vision models for industrial inspection, synthetic data, and model monitoring using Python, PyTorch, and Hugging Face.
Build and optimize GPU-accelerated inference software for large language models, focusing on agentic workloads like tool calling and multi-turn reasoning with Rust and Python.
About the Company Our client is a stealth AI startup backed by one of Southeast Asia's leading technology companies and is currently building its global founding team. The company is developing an AI-native…
Senior engineer builds and optimizes on-device AI inference software for NVIDIA GPUs, focusing on low-latency, memory-efficient local AI models using PyTorch, TensorRT, and related frameworks.
Senior engineer building high-performance, low-latency on-device AI inference software for NVIDIA’s RTX and DGX GPUs, optimizing models and runtimes like TensorRT and vLLM for local execution.
1. 主导AI编译器前/中/后端核心模块开发，实现计算图优化、算子融合、内存分配等关键技术； 2. 对接主流深度学习框架（PyTorch/TensorFlow），优化模型编译效率与推理性能； 3. 探索张量计算等优化算法，适配CNN/Transformer等复杂模型结构； 4. 主导构建模型适配、编译优化、测试验证全流程闭环智能Agent体系。 1. 计算机/软件工程/电子工程/微电子/数学等相关专业，硕士及以上学历优先； 2.…
1. 搭建 AI 编译器配套调试与性能分析工具链，涵盖 IR 可视化、性能剖析、精度自动化回归等能力； 2. 设计简洁易用的编译配置接口与上层 API，持续简化模型开发部署流程，提升开发者使用体验； 3. 研发模型编译可视化观测系统，实现编译过程、优化策略、推理性能指标可视化展示； 4. 面向算法团队提供编译落地支撑，定位模型编译与推理瓶颈，输出端到端调优解决方案； 5. 主导搭建模型适配、编译调优、测试验证一体化闭环智能…
Senior Data Scientist at Deloitte’s SFL Scientific team designs and deploys AI/ML models for clients, solving complex problems in areas like healthcare, autonomous systems, and consumer products using Python, PyTorch, and cloud platforms.
Dive in and do the best work of your career at DigitalOcean. Journey alongside a strong community of top talent who are relentless in their drive to build the simplest scalable cloud. If you have a growth mindset,…
1. 负责 CV、LLM、多模态模型面向端侧设备的轻量化算法研发，实现端到端推理性能优化； 2. 研究低精度量化算法（INT8/INT4 / 混合精度量化），解决量化误差、精度退化问题，完成量化校准、损失补偿方案落地； 3. 协同 AI 编译器、推理框架团队，针对 CNN、Transformer 开展算子优化、图结构改造、KV Cache 优化，提升端侧推理吞吐量、降低时延与内存占用； 4. 对接 PyTorch/ONNX…
Develops robust computer-vision systems by combining AI models with traditional algorithms for real-time applications, focusing on accuracy, latency, and edge deployment.
Build and optimize high-performance APIs and inference services to turn cutting-edge AI models into production-ready tools, using Python, FastAPI, CUDA, and cloud infrastructure.
About Us: Fireworks is the platform for specialized intelligence, enabling companies to build, train, and serve AI models tailored to their own data, workflows, and products. Founded by the team behind PyTorch and…
Designs and optimizes high-performance inference systems for large multimodal AI models, focusing on latency, throughput, and cost efficiency using frameworks like vLLM or TensorRT-LLM.
Job Title: Sr. Software Engineer - AI Location: India, Hybrid This is a hybrid position, which will require the ability to be onsite in our Bengaluru, India office as needed. Candidates must be based in India. ABOUT…
We couldn't check your fit for this role — add a CV to your profile to see it next time.
