Hands-on experience with large-scale language models (LLMs) and prompt engineering (e.g., GPT, BERT, T5 family). Familiarity with on-device or edge-AI deployments (e.g., TensorFlow Lite, ONNX, mobile/embedded inference). Knowledge of MLOps tooling (MLflow, Weights & Biases, Kubeflow, or similar) for experiment tracking and model governance. Open-source contributions or published papers in top-tier More ❯
computer vision and a strong understanding of model architectures like transformers and CNNs. Hands-on experience with model optimization (i.e. quantization, pruning) and model deployment frameworks such as TensorRT, ONNX Runtime, and OpenVINO. Proficiency with CUDA programming and optimizing code for GPU acceleration. Strong background in MLOps practices, including CI/CD using GitHub Actions and containerization with Docker. Excellent More ❯
computer vision and a strong understanding of model architectures like transformers and CNNs. Hands-on experience with model optimization (i.e. quantization, pruning) and model deployment frameworks such as TensorRT, ONNX Runtime, and OpenVINO. Proficiency with CUDA programming and optimizing code for GPU acceleration. Strong background in MLOps practices, including CI/CD using GitHub Actions and containerization with Docker. Excellent More ❯
computer vision and a strong understanding of model architectures like transformers and CNNs. Hands-on experience with model optimization (i.e. quantization, pruning) and model deployment frameworks such as TensorRT, ONNX Runtime, and OpenVINO. Proficiency with CUDA programming and optimizing code for GPU acceleration. Strong background in MLOps practices, including CI/CD using GitHub Actions and containerization with Docker. Excellent More ❯
model robustness on diverse datasets. Leading the full lifecycle of model development, from research and training to validation and performance benchmarking. Mastering model export to various formats such as ONNX, OpenVINO, and TensorRT to support a wide range of hardware. Working on model deployment strategies, including optimizing models for high-performance inference on both cloud and edge devices. Contributing to More ❯
model robustness on diverse datasets. Leading the full lifecycle of model development, from research and training to validation and performance benchmarking. Mastering model export to various formats such as ONNX, OpenVINO, and TensorRT to support a wide range of hardware. Working on model deployment strategies, including optimizing models for high-performance inference on both cloud and edge devices. Contributing to More ❯
Experience working with a modern cloud service (AWS, GCP, Azure etc.) Nice to Have Hands-on experience with autonomous driving systems Experience with model deployment with NVIDIA stack (e.g. ONNX graphs, TensorRT, profiling) Familiarity with recent breakthroughs in ML (e.g. foundation models, pre-training and efficient fine-tuning, multimodal Transformer architectures) Knowledge of autonomous driving, large-scale data curation pipelines More ❯
Experience working with a modern cloud service (AWS, GCP, Azure etc.) Nice to Have Hands-on experience with autonomous driving systems Experience with model deployment with NVIDIA stack (e.g. ONNX graphs, TensorRT, profiling) Familiarity with recent breakthroughs in ML (e.g. foundation models, pre-training and efficient fine-tuning, multimodal Transformer architectures) Knowledge of autonomous driving, large-scale data curation pipelines More ❯
Experience working with a modern cloud service (AWS, GCP, Azure etc.) Nice to Have Hands-on experience with autonomous driving systems Experience with model deployment with NVIDIA stack (e.g. ONNX graphs, TensorRT, profiling) Familiarity with recent breakthroughs in ML (e.g. foundation models, pre-training and efficient fine-tuning, multimodal Transformer architectures) Knowledge of autonomous driving, large-scale data curation pipelines More ❯
Experience working with a modern cloud service (AWS, GCP, Azure etc.) Nice to Have Hands-on experience with autonomous driving systems Experience with model deployment with NVIDIA stack (e.g. ONNX graphs, TensorRT, profiling) Familiarity with recent breakthroughs in ML (e.g. foundation models, pre-training and efficient fine-tuning, multimodal Transformer architectures) Knowledge of autonomous driving, large-scale data curation pipelines More ❯
environments Preferred Qualifications: Experience building ML models with wearable data (e.g., continuous heart rate, motion, respiration) Exposure to embedded AI or edge model deployment (e.g., TensorFlow Lite, Core ML, ONNX) Knowledge of healthcare data privacy and security (e.g., HIPAA, GDPR) Familiarity with GMLP (Good Machine Learning Practice) and clinical evaluation frameworks Seniority level Seniority level Not Applicable Employment type Employment More ❯
implementation. Extensive experience with common machine learning Python frameworks such as TensorFlow and PyTorch; and Python libraries such as pandas, and computer vision libraries such as OpenCV. Experience in ONNX and TensorRT. Very comfortable working in Linux environment. Familiarity with software development tools and agile development practices. 6 years experience in developing, optimizing, and testing deep learning in computer vision More ❯
instruments. Responsibilities Develop control software for our custom hardware stack (cameras, actuators, LEDs, fluidics). Build and synchronise image acquisition pipelines for multi-channel CMOS sensors. Deploy TorchScript/ONNX models for edge inference on embedded compute nodes. Design APIs and UI layers for translating AI output into researcher-friendly results. Take ownership of parts of the stack from device More ❯
bottlenecks, and optimizing them Good understanding of docker and containerization (Good to have) experience with Pytorch and Python3, and comfortable with C++ (Good to have) Understanding of Torch script, ONNX runtime, TensorRT (Good to have) Understanding of half-precision inference and int8 quantization What we offer 80-150k base Company equity % in an early-stage startup 100% company-paid More ❯
of two of the following compiler areas: Front-end - handle the handshaking of common Deep Learning Frameworks with Gensyn's IR for internal IR usage. Write transformation passes in ONNX to alter IR for middle-end consumption. Middle-end - write compiler passes for training-based compute graphs, integrate reproducible Deep Learning kernels into the code generation stage, and debug compilation More ❯
of two of the following compiler areas: Front-end - handle the handshaking of common Deep Learning Frameworks with Gensyn's IR for internal IR usage. Write transformation passes in ONNX to alter IR for middle-end consumption. Middle-end - write compiler passes for training-based compute graphs, integrate reproducible Deep Learning kernels into the code generation stage, and debug compilation More ❯
Preferred Qualifications: Experience building ML models with wearable data (e.g., continuous heart rate, motion, respiration). Exposure to embedded AI or edge model deployment (e.g., TensorFlow Lite, Core ML, ONNX). Knowledge of healthcare data privacy and security (e.g., HIPAA, GDPR). Familiarity with GMLP (Good Machine Learning Practice) and clinical evaluation frameworks. #J-18808-Ljbffr More ❯
Whetstone, Greater London, UK Hybrid / WFH Options
all.health
Preferred Qualifications: Experience building ML models with wearable data (e.g., continuous heart rate, motion, respiration). Exposure to embedded AI or edge model deployment (e.g., TensorFlow Lite, Core ML, ONNX). Knowledge of healthcare data privacy and security (e.g., HIPAA, GDPR). Familiarity with GMLP (Good Machine Learning Practice) and clinical evaluation frameworks. The successful candidates starting pay will be More ❯
engineering teams. Passion for open-source and decentralized infrastructure. Excellent communication and executive presence. Preferred Tech Stack Languages: Go, Rust, Python, Solidity AI Stack (plus): PyTorch, Hugging Face, Ray, ONNX What We Offer Competitive salary + equity/token package Flexible, remote-first work environment High-impact leadership role in a fast-scaling frontier tech company Opportunity to shape the More ❯
Enhance system reliability and observability, and manage system outages Research and implement optimizations for LLM inference Qualifications Experience with ML systems and deep learning frameworks such as PyTorch, TensorFlow, ONNX Knowledge of LLM architectures and inference optimization techniques (e.g., batching, quantization) Experience deploying scalable, reliable, real-time model serving systems (Optional) GPU architecture understanding or CUDA programming experience The compensation More ❯
a multiplatform inference backend. Our remote team is committed to advancing AI technology and making it broadly accessible. Responsibilities: Deploy machine learning models on edge devices using llama.cpp, ggml, onnx frameworks. Collaborate with researchers to code, train, and transition models to production. Integrate AI features into existing products, leveraging latest ML advancements. Requirements: Proficiency in Python, C, and C++ programming. More ❯
Cambridge, Cambridgeshire, United Kingdom Hybrid / WFH Options
Arm Limited
collaborating with remote teams across different time zones. "Nice To Have" Skills and Experience : Experience of Windows WDDM or Linux kernel driver development. Experience of AI frameworks (TensorFlow, PyTorch, ONNX). Knowledge of multimedia use cases including video, camera, display, and GPU. In Return: You will have the opportunity to demonstrate technical expertise and leadership skill to engage with GPU More ❯
from recent ML papers to solve practical challenges using retail image datasets Benchmark multiple approaches through rigorous experimental pipelines Build scalable inference pipelines using frameworks such as PyTorch, TensorRT, ONNX, and TensorFlow Lite (cloud and edge) Collaborate with engineers and product stakeholders to integrate models into end-to-end systems Perform error analysis and iterate on models continuously in production … models such as diffusion models and vision-language models (VLMs) Proficient in Python and familiar with ML frameworks like PyTorch Familiarity with model optimization and inference acceleration tools (e.g., ONNX, TensorRT, OpenVINO, vLLM) Demonstrated ability to ship ML models in production settings, including performance monitoring and failure analysis Excellent communication skills and proven ability to collaborate across cross-functional teams More ❯
DRW is a diversified trading firm with over 3 decades of experience bringing sophisticated technology and exceptional people together to operate in markets around the world. We value autonomy and the ability to quickly pivot to capture opportunities, so we More ❯
