Computational Photography Engineer

Computational Photography Engineer

Glass Imaging is looking for a Computational Photography Engineer, to work on advanced problems in topics such as Image Restoration, Image Alignment, Image Quality Assessment, and generally topics using Computer Vision and Deep Learning applied to smartphone photography.

You would be responsible for bringing the latest cutting edge ML powered Computational Imaging models into production on embedded devices and smartphones, from investigating, developing and training Deep Learning models and algorithms, to optimizing them for high throughput real time imaging applications. A strong background in signal + image processing; experience with generative image models, image restoration, or ML model compression is desired.

You should be familiar with cloud-based training of deep learning models, be proficient with tuning models and evaluating image quality with a photographic eye for detail.

Founded by former Apple Engineers who brought you Portrait Mode and other iPhone camera features, Glass is building the future of smartphone photography that delivers astonishing image quality. You’d be joining a unique team of creative and enthusiastic engineers with a passion and track record for revolutionizing the world of photography - and the future of camera technology in general.

• Strong Python skills + working knowledge of C/C++
• Expertise with Deep Learning implementations for imaging (e.g. Super-resolution, deconvolution, Denoising Diffusion generative models, NERF models, GANs, latest mobile-friendly CNN architectures, Image Transformers etc) with PyTorch or Tensorflow
• Model optimization & ML Ops experience - knowledge distillation, hyperparameter tuning, distributed training, building efficient data loaders & image preprocessing pipelines
• Computational photography methods. Inverse imaging:
  Super-resolution, deconvolution, in painting. Knowledge of camera calibration, optics, lens design, color science, image quality
• Passion for keeping up to date with the latest AI research
• Excellent communication, analytical and problem solving skills, strong self motivation
• 3+ years of relevant Industry experience (ideal) or completed MSc or PhD in a related technical field

• Android or iOS development
• Image quality analysis skills - strong eye for detecting artifacts in images and understand typical ISP tuning
• Image processing, graphics & ML / Computer Vision algorithms, e.g.:
  Stereo Depth estimation, Guided/Bilateral filtering, feature matching, style transfer, iterative algorithms, BLAS;
  Libraries such as OpenCV; ISP (demosaic, denoise, HDR etc);
• Embedded ML model optimizations: compression & sparsification, Neural Engines or converting models for dedicated AI hardware
• Embedded real-time algorithm implementations: GPU optimizations; general parallel programming techniques with e.g. OpenCL, CUDA, Metal may be useful.
• Work with solutions tailored to Qualcomm Snapdragon GPUs/ISP/DSP. Knowledge of GPU Kernel performance tuning, profiling, cache usage, memory access patterns / architecture optimization, quantization.
• Low level drivers, hardware interfaces, image sensors, FPGAs
• Published papers in relevant technical conferences (CVPR, ICCP, ICCV, NeurIPS etc).

Glass Imaging has both software-only (AI based) and software+hardware (AI plus custom optical design) solutions to improve smartphone camera quality.

On the software only side, our edge AI processing algorithms can replace the front end of a traditional camera ISP pipeline to correct the optical defects of lenses, perform joint demosaicing, deconvolution, denoising, and super-resolution, and run on a phone’s GPU, Neural Engine or similar, to give ultra-detailed high fidelity images in near-real-time. Such solutions can be embedded into

On the software+hardware side, Glass's innovative camera architecture combines a new type of lens with state-of-the-art AI algorithms to form an image on a large image sensor while keeping the overall thickness of the camera module thin enough to fit in any smartphone.

The result is a camera module that eliminates the need for multiple lenses and the complexity that comes with it. Our technology drastically improves image quality to enable features like real HDR, Portrait Video, 10-15x resolution gain and 20x less noise for low light imaging, and more, i.e. the quality of a DSLR with the smartphone camera app experience, in your pocket.

Our business model is based around licensing our unique technology to a $40B+ market.

We are a well funded VC backed seed-stage startup with great benefits (including stock options, competitive pay, 401k, and health insurance), a small (but growing) and friendly team. We are all passionate about photography and hope you are too! We strongly prefer applicants based in or able to relocate to Bay Area, though remote/hybrid may be possible in the right circumstances.

Apply here: