LOOKING FOR A NEW ADVENTURE?

Speedinvest and our portfolio of startups are always hiring exceptional talent!
Browse open jobs below to find your next career move.
226
companies
1,123
Jobs

C++ Software Engineer (Performance)

Deep Render

Deep Render

Software Engineering
London, UK
Posted on Friday, June 23, 2023
Deep Render is a Deep Tech startup founded to liberate the world of all bandwidth constraints by pioneering AI-Compression technology. Our compression codecs are based on a fundamental technology shift, representing over 100 years of progress in the industry.We're leading the way in AI-Compression, having the world's first AI-Codec running in real-time on mobile devices. Our team comes with 50+ years of combined research experience with over 40+ filed patents.Deep Render has recently raised its Series A funding round from top-tier investors and is looking to double/triple its current 20-person team. We're in commercial engagements with some of the largest Big Tech companies in the world and expect hundreds of millions of people to use the Deep Render AI Codec by 2024.Responsibilities:
  • Work in a team to port ML research algorithms to edge devices with an initial focus on smartphones (Android, iOS)
  • Profile various algorithms to analyse performance and identify any bottlenecks. Profiling includes data loading, data movement, data caching, operation count, execution chipset, warm-up latency and others
  • Implement solutions to the identified bottlenecks
  • Implement a high-performance entropy coding algorithm, e.g. Range Coding or Asymmetric Numeral Systems, across different hardware architectures
  • Optional: Write custom operations using the low-level API for Android (OpenGL ES) and iOS (Metal) systems
  • Optional: Apply standard neural network runtime optimisation methods such as pruning, low-bit quantisation, architecture tuning, batching and others
Must have:
  • At a minimum, a Bachelor's degree in computer science or related field (Mathematics, Physics, Engineering)
  • Expertise in C++
Preferred skills:
  • At a minimum, 3-5 years of experience in performance optimisation
  • Some experience with optimisation techniques. Examples include SIMD (SSE, AVX), vectorisation, loop dependencies, multithreading, multi-processor usage, and tensor cores
  • Experience working in an ML focused environment or exposure to PyTorch/TensorFlow