Founding ML Engineer

About the role

Base Compute is building the next generation of on‑device AI infrastructure. As a Founding ML Engineer you will work at the intersection of systems engineering and machine learning, turning cutting‑edge research into production‑ready, high‑performance inference stacks.

Key responsibilities

• Develop and scale a custom inference engine, handling weight loading, KV‑cache management and request scheduling.
• Write and tune hardware‑specific kernels for Apple Silicon, NVIDIA, AMD, Snapdragon and other edge platforms.
• Design low‑latency serving runtimes in C++ for model routing, continuous batching and novel decoding strategies under strict thermal and memory limits.
• Profile performance across the stack and eliminate bottlenecks from memory bandwidth to kernel interleaving.

Required profile

• 3+ years of experience in ML engineering or systems programming (Rust, C/C++).
• Proven ability to build performance‑critical software and take ownership of ambiguous architectural challenges.
• Strong communication skills to explain complex decisions, give feedback and document systems clearly.

Required skills

• GPU programming and hardware optimization (CUDA, ROCm, Metal, Triton or similar).
• Deep understanding of modern LLM architectures, quantization, speculative decoding and related optimization techniques.
• Experience with low‑level systems development in C++ and Rust.

What we offer

• Founding team equity and a competitive base salary.
• Direct influence on technical direction and roadmap.
• Opportunity to solve genuinely hard, unsolved problems in a small, fast‑moving team.