Staff Inference Systems Engineer — High-Throughput AI

Kindredventures; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

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).

Responsibilities

• 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.

Skills

Inference systems

Distributed compute

GPU optimization

PyTorch

JAX

Maintainable code

Tools

TensorRT

Kubernetes

Ray

Slurm

Job description

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.