Member of Technical Staff — Inference Infrastructure

Kindredventures; San Francisco (CA); Sur place; USD 180 000 - 240 000; Plein temps

Résumé du poste

Kindredventures is recruiting infrastructure engineers to scale large-scale inference and evaluation around a physics-based LPM initiative. You will work on high-throughput systems, latency-optimized serving, and distributed orchestration across Kubernetes, Ray, and Slurm.

Ideal candidates have a track record in building efficient inference stacks, GPU-aware optimization, and deep learning frameworks like PyTorch or JAX. Collaboration with researchers and a focus on reliability are essential.

Qualifications

• Experience building or optimizing inference/serving systems for throughput and latency.
• Understanding of distributed compute, GPU parallelism, and hardware-aware optimization.
• Deep familiarity with deep learning frameworks (PyTorch, JAX) and their underlying system architectures.
• Strong engineering skills: performant, maintainable code and the ability to debug complex codebases.
• Bonus: contributions to open-source inference or systems infrastructure (e.g. vLLM, Triton).

Responsabilités

• Build high-throughput inference systems for large-scale evaluation, backtesting, and scoring against historical observations.
• Design and implement techniques to improve latency, throughput, and efficiency for real-time inference.
• Optimize the inference stack to fully utilize hardware FLOPs, bandwidth, and memory.
• Extend orchestration frameworks (Kubernetes, Ray, Slurm) for distributed inference and large-batch evaluation sweeps.
• Establish standards for reliability, observability, and reproducibility across the inference stack.
• Collaborate with researchers to enable high-performance inference for novel architectures as they emerge.

Connaissances

Inference systems

Distributed compute

GPU optimization

PyTorch

JAX

Maintainable code

Outils

TensorRT

Kubernetes

Ray

Slurm

Description du poste

Our mission is general causal intelligence; AI that is capable of (1) predicting the future and (2) identifying the actions to alter it.

To achieve this breakthrough, we are building a Large Physics foundation Model (LPM) because physical systems, unlike text or images, are governed by verifiable cause and effect. We believe that scaling on physics will enable an understanding of causality required to predict and control physical systems, starting with weather.

Our founding team has built and deployed AI against the physical world in robotics, drug discovery, and particle physics at institutions like DeepMind, Waymo, Cruise, Insitro, Nabla Bio, and CERN.

We look for infrastructure engineers who are excited to tackle unsolved problems. Progress on an LPM is gated by how fast we can evaluate it: large-scale backtesting against decades of physical observations, ensemble generation, and rollout evaluation across model scales.

Responsibilities

• Build high-throughput inference systems for large-scale evaluation, backtesting, and scoring against historical physical observations
• Design and implement techniques that improve latency, throughput, and efficiency for real-time inference
• Optimize the inference stack to fully utilize hardware FLOPs, bandwidth, and memory
• Extend orchestration frameworks (e.g. Kubernetes, Ray, Slurm) for distributed inference and large-batch evaluation sweeps
• Establish standards for reliability, observability, and reproducibility across the inference stack, so every evaluation is trustworthy and repeatable
• Collaborate with researchers to enable high-performance inference for novel architectures as they emerge

What we're looking for

We value a relentless approach to problem-solving, rapid execution, and the ability to quickly learn in unfamiliar domains.

• Experience building or optimizing inference and serving systems for throughput and latency (e.g. TensorRT)
• Understanding of distributed compute, GPU parallelism, and hardware‑aware optimization
• Deep familiarity with deep learning frameworks (e.g. PyTorch, JAX) and their underlying system architectures
• Strong engineering skills: performant, maintainable code and the ability to debug complex codebases
• Bonus: contributions to open-source inference or systems infrastructure (e.g. vLLM, SGLang, Triton)