ML Engineer
About us
Mirai builds the fastest on-device inference engine for Apple Silicon. In under a year, a 14-person team built a full stack, from model optimization to a proprietary runtime, outperforming MLX and llama.cpp on supported models.
We’re making local inference practical, fast, and reliable for real products.
Why us?
Mirai is founded by proven entrepreneurs who built and scaled consumer AI leaders like Reface (200M+ users, backed by Andreessen Horowitz) and Prisma (100M+ users). Our team is small (14 people), senior, and deeply technical. We ship fast and own problems end-to-end.
We’re advised by a former Apple Distinguished Engineer who worked on MLX, and backed by leading AI-focused funds and individuals.
- Design evaluation metrics and benchmarks.
- Build data processing and labeling pipelines.
- Experiment with model architectures and training methods.
- Contribute to our training and model optimization framework
- Strong background in Deep Learning, with deep knowledge of modern text foundation models
- Solid grasp of statistics and probability theory
- Understanding of ML performance optimization landscape
- Experience building complex training pipelines from scratch
- Very strong software engineering skills.
Bonus:
- Experience with JAX
- Experience with GPU programming
- Knowledge of Rust
You are probably a good fit if you have a thorough understanding of such concepts as:
- muP
- Muon
- FSDP
- FlashAttention
- SigLIP
Remote / SF / Europe