Logo
MulticoreWare Inc.

Video Engineer - Deep Learning | Chennai | Experience: 3 - 8 years Job at Multic

MulticoreWare Inc., California, MO, United States, 65018

Save Job

Chennai City Corporation, India | Posted on 24/02/2025

  • Department Name: Applications & Algorithms
  • Job Type: Full time
  • Date Opened: 24/02/2025
  • Industry: Software Development
  • Minimum Experience: 4 years
  • Maximum Experience: 8 years
  • City: Chennai City Corporation
  • Province: Tamil Nadu
  • Country: India
  • Postal Code: 600015

About Us

MulticoreWare is a global software solutions & products company with its HQ in San Jose, CA, USA. With worldwide offices, it serves its clients and partners in North America, EMEA, and APAC regions. Started by a group of researchers, MulticoreWare has grown to serve its clients and partners on HPC & Cloud computing, GPUs, Multicore & Multithread CPUs, DSPs, FPGAs and a variety of AI hardware accelerators.

MulticoreWare was founded by a team of researchers that wanted a better way to program for heterogeneous architectures. With the advent of GPUs and the increasing prevalence of multi-core, multi-architecture platforms, our clients were struggling with the difficulties of using these platforms efficiently.

We started as a boot-strapped services company and have since expanded our portfolio to span products and services related to compilers, machine learning, video codecs, image processing and augmented/virtual reality. Our hardware expertise has also expanded with our team; we now employ experts on HPC and Cloud Computing, GPUs, DSPs, FPGAs, and mobile and embedded platforms. We specialize in accelerating software and algorithms, so if your code targets a multi-core, heterogeneous platform, we can help.

Job Description

Video Deep Learning Engineer: (min 4-5 years’ experience)

We are currently looking for bright Video Deep Learning talent who have 4-5 years of industry experience, working on problems related to the Video AI space.

The ideal candidate will be proficient in implementing and optimizing ML/DL/AI models, particularly for video and image processing, while also having a deep understanding of encoding and decoding algorithms. If you are passionate about advancing multimedia technologies and have hands-on experience with deep learning and video compression standards, we encourage you to apply.

As part of our team, you will work on cutting-edge projects in video and image compression, activity detection, object detection, and related areas. You will be responsible for implementing, tuning, and evaluating ML/DL models, optimizing performance, and applying your expertise in compression algorithms to improve encoding/decoding efficiency.

Minimum Qualifications

  • Execution of ML/DL/AI models on PyTorch or any other framework, loss and performance analysis, regression tracking.
  • Good understanding of Deep Learning concepts (model parameters, tuning of models, optimizers, learning rates, attention mechanisms, masking, etc).
  • Thorough understanding of deep learning implementations of activity detection or object detection.
  • Expertise in video and image compression standards (such as H.264, HEVC, AV1, JPEG) and relevant encoding/decoding algorithms.
  • Proficiency in using quality metrics such as SSIM, PSNR to evaluate encoding/decoding performance.
  • Experience with hardware acceleration techniques in multimedia processing is a plus.
  • Expertise in numeric analysis, loss/accuracy, and performance debug in validation environment.
  • Solid development experience (git, cmake, gdb, strace, shell, etc.) in Unix-like (Linux) environment. The candidate must be able to identify and debug system issues.
  • Proficiency in version control tools like GIT, GITLab, Gerrit Reviews.
  • Experience with the Agile/Scrum processes through the entire SDLC: software design, coding, unit test, integration test, build and release.

Preferred Qualifications

  • Good understanding of DALI / FFMPEG / gstreamer encoding, decoding and pre-processing functions.
  • Knowledge of deployment tools like Triton inference server or Ray is a plus.
#J-18808-Ljbffr