Senior Machine Learning Engineer

What You'll Be Doing

What We’re Looking For

Nice to have

• Experience optimizing inference workloads in GPU environments
• Experience with vLLM or custom inference servers
• Experience with diffusion models, LLMs, or multimodal architectures more broadly
• Experience with Kubernetes, Docker, or containerised ML workloads
• Experience building internal ML tooling or developer-facing APIs
• Experience working in high-throughput distributed systems
• Background in AI media generation (image, video, audio)

Benefits

• We’re a remote-first team that comes together in person twice a year to plan, collaborate, and celebrate wins. Day to day we keep a few core hours for teamwork, but outside of that you set the schedule that helps you do your best work.
• We move quickly and hold a high bar, but we also believe sustainable performance matters. After major releases and milestones, we create space for the team to properly unplug, recharge and come back with the energy to tackle what's next.
• Generous paid time off – vacation, sick days, public holidays
• Meaningful stock options – share in the upside you create
• Remote-first setup – work from home anywhere we can employ you
• Flexible hours – own your schedule outside core collaboration blocks
• Family leave – paid maternity, paternity, and caregiver time
• Company retreats – twice-yearly gatherings in inspiring locations

Qualifications

• What We’re Looking For
• Deep, hands-on expertise in Python and PyTorch, comfortable working at a level well beyond standard framework usage, including the quirks and edge cases that come with pushing Python for ML workloads
• Demonstrated experience building ML applications and models yourself, not just running or deploying existing ones (e.g. serving a pre-built model via vLLM doesn't qualify on its own)
• Hands-on experience writing GPU kernels in CUDA/C++, or in Triton
• Low-level experience with model internals e.g. working directly with diffusion model architectures (diffusers or equivalent), not just calling high-level APIs
• Experience with the PyTorch compiler (torch.compile) or comparable low-level PyTorch tooling
• Practical experience fine-tuning large models as a repeatable service (LoRA, PEFT, adapters), built for speed and reuse across many models, not a single one-off training run
• Real, verifiable project history e.g. GitHub repos, demonstrating what you have personally wrote
• High ownership and comfort operating in a fast-paced startup environment