Tldr: on-device AI lab, from founders of Prisma / Reface (100+ mln users), $10 mln raised, fully remote. 2 roles - ML Research Engineer, Inference Engineer ** About the company:**

Mirai is an AI lab developing a foundational model and inference infrastructure for on-device AI, enabling LLMs to run locally with ultra-low latency.

📱 Today, the AI economy scales poorly through cloud computing and GPU inference. Over time, a significant portion of AI workloads will move from servers directly to user devices.

🔝 The company was founded by the founders of Prisma labs (one of the pioneers of on-device ML) and Reface (100+ million users), and has raised $10 million in a seed round.

Fully remote, distributed team (from London to Tokyo), English is the primary working language.

Position - ML Research Engineer

Main directions: — quantization — speculative decoding — optimization for LLM inference — NLP / transformer research

What you will do: — research and implement new approaches to model optimization — read and adapt research papers on NLP / LLM systems — write production-quality ML systems

We are interested in candidates with experience in: — Deep Learning / NLP / transformers / LLMs — ML research / publications / open-source projects — training, fine-tuning, or optimizing models

Will be a plus: — research labs / Kaggle / ICPC / olympiads — experience implementing paper → production pipeline

Contact - @ann_rish