ML Inference Engineer San Francisco · Engineering · Full Time →

Reactor; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

Visa sponsorship

Relocation support

Generous health, dental, and vision coverage

Job summary

Reactor is looking for an experienced ML Inference Engineer with deep expertise in high-performance ML engineering. This role focuses on optimizing the performance of generative media models, contributing to Reactor's competitive edge.

The ideal candidate will drive model performance for diffusion models, collaborate with partner teams, and implement optimizations. A Bachelor's degree in a related field is required, along with strong knowledge of GPU hardware and modern ML optimization techniques. The position offers competitive salary and meaningful equity.

Qualifications

• Strong foundation in systems programming, with a track record of identifying and resolving bottlenecks.
• Working knowledge of GPU hardware (NVIDIA).
• Strong understanding of transformer architectures and modern ML optimization techniques.

Responsibilities

• Drive frontier position on model performance for diffusion models.
• Design and implement a in-house inference runtime.
• Profile and benchmark model performance to identify computational bottlenecks.

Skills

Deep expertise in PyTorch

TensorRT

Advanced serving architectures

Model compilation

Quantization

Education

Bachelor's degree in Computer Science, Electrical Engineering, or related

Tools

Nsight

ONNX Runtime

Job description

We're looking for an ML Inference Engineer with deep expertise in high-performance ML engineering. This is a highly technical, high-impact role focused on squeezing every drop of performance from generative media models.

You'll work across the inference stack, designing novel frameworks, optimizing inference performance, and shaping Reactor's competitive edge in ultra-low-latency, high-throughput environments.

What You'll Do

• Drive our frontier position on model performance for diffusion models
• Design and implement a high-performance in-house inference runtime
• Implement optimizations using torch.compile, custom CUDA kernels, and specialized inference frameworks
• Optimize neural network models through quantization, pruning, and architectural modifications
• Profile and benchmark model performance to identify computational bottlenecks
• Collaborate directly with model partner teams to integrate their models into our platform

What We're Looking For

• Bachelor's degree in Computer Science, Electrical Engineering, or a related technical field (or equivalent practical experience)
• Strong foundation in systems programming, with a track record of identifying and resolving bottlenecks
• Deep expertise in PyTorch, TensorRT, TransformerEngine, Nsight, ONNX Runtime
• Model compilation, quantization (INT8/FP16), and advanced serving architectures
• Working knowledge of GPU hardware (NVIDIA)
• Strong understanding of transformer architectures and modern ML optimization techniques
• Competitive SF salary and meaningful early equity
• Visa sponsorship and relocation support
• Generous health, dental, and vision coverage