Deep Learning Jobs

Train OpenWakeWord with a Custom Wake Word (High Accuracy, Low False Positives) Project Overview I am looking for an experienced AI/ML engineer to train OpenWakeWord with a custom wake word. The goal is to build a production-quality wake word model that is highly accurate, responsive, and resistant to false activations. Scope of Work * Train a custom OpenWakeWord model from scratch or fine-tune an existing pipeline. * Use real positive voice samples from multiple speakers, accents, speaking speeds, distances, and environments. * Collect and use a large negative dataset containing similar-sounding words, random conversations, TV/audio, background noise, music, and other speech to minimize false positives. * Optimize the model for: * High detection accuracy * Extremely low false ...

I want my Freelancer.com profile to speak clearly to clients who need either artificial-intelligence expertise, solid data-entry support, or a mix of the two. To make that happen I need a professional-sounding overhaul that includes every public-facing section: headline, summary, skills list, portfolio hints, picture and cover image recommendations, even the “why hire me” snippets. Here’s what I expect you to deliver: • A concise, informative headline that instantly positions me as a dual AI & data-entry specialist. • A polished summary written in a strictly professional tone, showing how the analytical rigour of AI pairs with the accuracy and speed of data entry. • A curated skills roster (Freelancer keyword format) prioritising AI, machine lear...

I’m looking for an **expert Computer Vision / YOLO specialist** to optimize my existing object detection model. I already have: * PC with NVIDIA GPU * Dataset and annotations * Training environment/setup * Existing YOLO model and baseline results ### What I need I need someone experienced who can **analyze the dataset and model, experiment with training parameters, augmentations, image size, batch size, learning rate, model configuration, etc., and achieve the best possible results.** This is **not just a training job**. I want someone who can analyze false positives/negatives, identify weaknesses, run experiments, compare results, and intelligently tune the model. Remote access to my PC will be provided. **Experience with YOLO, PyTorch, object detection, small-object/drone de...

Hi, I’m working on my PhD project on **AI-based detection of patient–ventilator asynchrony (PVA) from ventilator waveforms**, and I’m looking for a Python/AI developer. The project will involve: 1. **Physics-based synthetic waveform generation** using lung-mechanics equations to generate realistic Paw, flow and volume signals, initially focusing on normal breathing and double triggering. 2. **Synthetic dataset creation** with waveform signals, images, labels and physiological parameters. 3. Addition of realistic **noise, artefacts and physiological variability**, followed by diffusion-based augmentation. 4. Development of AI models using **time-series and waveform images**, including Transformers, CNNs, Bi-LSTM and Swin Transformer. 5. **Multimodal fusion** of signal an...

**Job Title:** Computer Vision / Roboflow Expert – Fine-Tune Model for PPE & Kitchen Hygiene Violations **Project Description:** We are developing an AI-driven restaurant and kitchen safety monitoring system. We need an experienced Computer Vision & Deep Learning Engineer to build, annotate, and fine-tune a high-accuracy object detection/segmentation model (using Roboflow and YOLO models like YOLOv8/v11) to accurately detect specific hygiene violations in real-time CCTV feeds. **Key Challenges & Core Requirements:** 1. **Glove Compliance:** * Detect bare hands vs. gloved hands (handling fine-grained vision tasks on food prep surfaces). * Accurately flag "No Gloves" violations when staff are touching/preparing food. 2. **Proper Mask Wearing:** * Detect prope...

We need an AI-focused application that delivers 100% functionality in analyzing and solving geometric patterns in jewellery. The primary objective is to ensure precision and reliable output. The features include: 1. Detecting patterns across different jewellery parts such as any parts of boundaries, textures, cuts, or design elements (including broad patterns, sub-patterns, and intricate sub-to-sub patterns). 2. Identifying low-quality or unclear components within these patterns and seamlessly replacing them with high-quality elements from other sources. 3. Ensuring replacements naturally blend into the overall piece, maintaining structural integrity and visual coherence. The focus is entirely on achieving accurate functionality with results that meet expectations directly. Experienced f...

I have a private collection of images that I want to sort automatically, and I need your expertise to build and fine-tune an image-classification pipeline. The dataset is purely visual—no accompanying text or numerical metadata—so the focus is on extracting meaningful visual features and assigning each image to the correct category. My end goal is straightforward: a reliable model that can classify every new photo I add, with clear metrics that show its accuracy. I haven’t fixed the exact number of categories yet; we can review the sample set together and decide what makes sense. You are free to work in Python with libraries such as TensorFlow, Keras or PyTorch, and any supportive tools for preprocessing, augmentation, and evaluation. I’ll share the image folder...

Project Description We are looking for an experienced AI Video Analytics developer or company that already has an existing AI video analytics platform or can quickly develop a demo for client presentation. Important: We are not looking for a full development project from scratch at this stage. Our immediate requirement is a working demo or existing software that can be integrated with Matrix IP Cameras. If the demo is approved, the selected developer/team will be awarded the complete development and customization project. Immediate Requirement We prefer candidates who can provide either: An existing AI Video Analytics software with a live demo. A ready-to-use MVP (Minimum Viable Product). A prototype that can be completed within a short timeframe (7–15 days). A presentation-rea...

I need a hands-on partner to turn a folder of labelled pictures into a production-ready image-classification model. This project sits squarely in machine learning: the main task is to build, train, and validate a solution that can correctly place each incoming image into its predefined category with solid, measurable accuracy. Here is how I see the work unfolding: • Prepare and clean the image dataset, applying sensible augmentation so the network generalises well. • Select or design a CNN architecture (transfer-learning with ResNet, EfficientNet, or a custom model—whichever you believe will perform best) and implement it in Python using TensorFlow or PyTorch. • Train, tune hyper-parameters, and track performance with clear metrics; I want the training notebo...

The project centers on building a production-ready TensorFlow 2.x model that classifies tabular data delivered to us through an internal API. I have the API specifications and sample payloads ready; you will turn those streams into a clean training pipeline, engineer the right features, and iterate until the classifier meets our performance targets in real-world tests. Scope of work • Data pipeline – pull the API data, handle preprocessing, and produce TensorFlow-friendly datasets for train/val/test splits. • Model development – design, train, and tune a deep learning architecture suitable for tabular inputs (e.g., wide & deep, Transformer, or other proven structures). • Optimization – experiment with hyperparameters, regularization, and callback...

J’ai plusieurs enregistrements audio à contenu affaires et je souhaite recevoir, pour chacun : • une transcription fidèle de ce qui est dit ; • la traduction complète en français présentée à la suite ou en colonne séparée. Le ton doit rester professionnel et cohérent avec un contexte business. Si des termes techniques ou des noms propres apparaissent, merci de les conserver ou de les expliquer brièvement entre crochets quand c’est pertinent. Format attendu : document Word ou Google Doc, ou fichier .srt si vous préférez fournir un fichier sous-titré avec time-codes basiques (flexible sur le format tant que lecture et révision restent simples). Je fournirai les fi...