Role description
Archetype AIAbout Us
At Archetype AI, we’re building the world’s first physical AI platform to bring artificial intelligence into the real world. Our foundation model, Newton, understands the physical world through objective sensor data and generates real-time insights into complex physical behaviors, from industrial machinery and systems to wearable devices and smart environments.
Formed by a high-caliber team from Google and backed by one of Silicon Valley’s most renowned venture funds, Archetype AI is at Series A and rapidly advancing its technology for the next big leap. This is a unique opportunity to join an exciting, fast-growing AI team based in the heart of Silicon Valley.
About the Role
You will own the serving path for Newton and related multimodal models. Much of our inference stack is Rust-native: model nodes in our agent runtime, built on Rust ML stacks (candle, Burn) with custom GPU kernels, plus the routing layer that streams real-time inference to GPU nodes. You will drive GPU utilization, numerical precision, and low-latency serving from the kernel up.
What You’ll Own
Build and own model nodes in our Rust inference runtime: loading, warmup, batching, streaming, GPU memory pools.
Optimize kernels and the GPU path: custom CUDA kernels, mixed precision, quantization, parity against research.
Own inference routing and serving: streaming path API to GPU node, request batching, SLO-backed latency and cost.
Productionize research checkpoints: export, compilation, quantization, parity evals, and rollout.
Build the observability inference needs: latency histograms, GPU metrics, OOM signatures, replayable traces.
Key Qualifications
6+ years software engineering, several of them in ML systems, inference, or high-performance GPU computing.
Has owned a production serving path end to end, not only benchmarked models.
Expert in PyTorch with models shipped to production; knows what will be slow before the profiler runs.
Strong CUDA or equivalent GPU depth: memory hierarchy, occupancy, Nsight or equivalent profiling.
Rust or C++ alongside Python, Linux performance, production ops; ready to work in Rust daily.
Works with researchers: can translate an architecture change into serving work.
Nice to Have
Rust ML stacks: candle, Burn, or comparable GPU compute in Rust.
Custom kernels and compiler stacks: Triton, CUTLASS, TorchInductor, TensorRT.
Quantization and mixed precision in production with a numerical-correctness suite.
Multimodal, video, embedding or time-series serving, not only decoder-only chat LLMs.
High-performance serving stacks (vLLM, SGLang, TensorRT-LLM): continuous batching, paged KV cache.