2 of 2 Remote/Hybrid Flash Jobs in the East of England

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

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 ...