‹ All jobs
ML Researcher
<h2>About Us</h2><p style="min-height:1.5em">Base Compute is an AI inference lab. Our mission is to bring AGI on device. We believe in a world where everyone has access to intelligence: fast, private and always available on your device.</p><p style="min-height:1.5em">We’re building the infrastructure for the next generation of on-device AI, from silicon-level optimizations to distributed inference systems.</p><p style="min-height:1.5em">We’re working on hard problems at the intersection of inference efficiency, model intelligence and autonomous research.</p><p style="min-height:1.5em"></p><h2>The Role</h2><p style="min-height:1.5em">We’re looking for a Founding ML Researcher to work at the frontier of on-device AI. This role is for someone who identifies problems and potentials, designs and executes experiments and derives insights that translate into real-world performance.</p><p style="min-height:1.5em">You’ll have significant ownership over our research agenda and direct influence on the technical bets the company makes.</p><p style="min-height:1.5em"></p><h2>What You’ll Work On</h2><ul style="min-height:1.5em"><li><p style="min-height:1.5em"><strong>Inference research</strong>: Identifying and validating new approaches to on-device efficiency, including speculative decoding variants, novel quantization schemes and entirely new techniques yet to be discovered</p></li><li><p style="min-height:1.5em"><strong>Model routing research</strong>: Building the intelligence that decides how requests are served between on-device vs. frontier API models</p></li><li><p style="min-height:1.5em"><strong>Autoresearch pipelines</strong>: Designing systems that can autonomously explore, hypothesize and evaluate research ideas that accelerate our R&D loop</p></li><li><p style="min-height:1.5em"><strong>Evaluations and benchmarks</strong>: Developing rigorous evals that measure performance in the real world, outside of clean academic settings</p><p style="min-height:1.5em"></p></li></ul><h2>What We’re Looking For</h2><ul style="min-height:1.5em"><li><p style="min-height:1.5em">PhD in ML or equivalent industry research experience</p></li><li><p style="min-height:1.5em">Deep understanding of LLM architectures and the principles of AI inference</p></li><li><p style="min-height:1.5em">Expertise in a relevant topic, such as speculative decoding, quantization theory, model distillation, reinforcement learning</p></li><li><p style="min-height:1.5em">A track record of producing results that people build on: research papers, open-source projects or blog posts that prove out novel ideas</p></li><li><p style="min-height:1.5em">Good communication: the ability to explain complex ideas simply, give honest feedback and document findings in a reproducible way</p></li><li><p style="min-height:1.5em">Nice-to-haves:</p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Familiarity with GPU and accelerator architectures and kernel optimization (CUDA, ROCm, Metal, Triton, etc.)</p></li><li><p style="min-height:1.5em">Experience deploying models under on-device constraints (memory bandwidth, latency budgets, and thermal and power ceilings)</p></li></ul></li></ul><p style="min-height:1.5em"></p>