2 of 2 Flash Jobs in the East of England

transformer architectures (e.g., GQA, KV-caching) and best practices Expertise in distributed training techniques Familiarity with optimisation strategies for model inference (e.g., dynamic batching, flash attention, speculative decoding) Proven track record of developing and deploying models at scale Expertise in Python, ML frameworks (TensorFlow, PyTorch), and experience with cloud ...

complete chip or significant subsystem Deep understanding of modern microcontroller and processor architectures, including: Real-time operation and deterministic interrupt handling Low-power architectures Flash and SRAM hierarchies Common peripheral interfaces such as SPI, I2C, UART, USB, ADC/DAC, timers, and programmable I/O fabrics Strong knowledge ...