AI Systems Performance Engineer - Scalable LLM Inference

SambaNova Systems; San Jose (CA); On-site; USD 135,000 - 165,000; Full time

Benefits offered by this job

Equity

Health insurance

Well-being benefits

Job summary

SambaNova Systems is seeking an AI Systems Performance Engineer to bring up and optimize foundation models on its reconfigurable dataflow platform. You’ll work with cutting-edge models like LLMs and multimodal architectures, profiling across model, compiler, runtime, and hardware layers to improve throughput, latency, and memory efficiency.

You will collaborate with ML, compiler, runtime, and hardware teams, exploring new techniques in architecture, quantization, scheduling, and memory

Qualifications

• Bachelor's or Master's degree in computer science, electrical engineering, computer engineering, or a related technical field (completed or expected before start date).
• Strong programming skills in Python, C++, or a similar language.
• Foundations in algorithms, data structures, computer architecture, operating systems, or parallel computing.
• Familiarity with deep learning and at least one major ML framework (PyTorch, TensorFlow, JAX).
• Strong analytical and problem-solving skills with interest in system performance.
• Ability and enthusiasm to learn across ML, software systems, and hardware.

Responsibilities

• Bring up foundation models on SambaNova platform through software stack.
• Analyze and profile model execution to identify bottlenecks across model, compiler, runtime, and hardware layers.
• Optimize AI workloads for throughput, latency, memory efficiency, and scalability.
• Collaborate with ML, compiler, runtime, and hardware engineers on high-performance AI applications.
• Explore and integrate techniques in model architecture, quantization, scheduling, caching, and memory optimization.
• Develop tools, benchmarks, and performance analysis methodologies for large-scale AI inference.
• Investigate new model architectures and translate research into efficient production implementations.
• Contribute ideas for dataflow, scheduling, and system optimizations for single-node and distributed inference.

Skills

Python

C++

Algorithms & data structures

DL frameworks

Education

Bachelor's or Master's degree in CS/EE/CE or related field

Tools

CUDA

Triton

OpenCL

vLLM

DeepSpeed

Megatron

TensorRT

Job description

SambaNova Systems is seeking an AI Systems Performance Engineer to bring up and optimize foundation models on its reconfigurable dataflow platform. You’ll work with cutting-edge models like LLMs and multimodal architectures, profiling across model, compiler, runtime, and hardware layers to improve throughput, latency, and memory efficiency.

You will collaborate with ML, compiler, runtime, and hardware teams, exploring new techniques in architecture, quantization, scheduling, and memory