SambaNova
AI Performance Engineer - New Grad
$131K–$197K
Austin, Texas, United States +3 · Entry level · Full-time · Posted Oct 20, 2026
- Location
- Austin, Texas, United States
San Jose, California, United States
Austin, Texas, United States
San Jose, California, United States - Education
- B.S. in Computer Science, Electrical Engineering, or related field
About the job
Brings up and optimizes foundation-model inference on SambaNova’s dataflow platform by profiling performance and improving throughput and latency.
What you'll do
- Bring up foundation models and profile performance across compiler, runtime, and hardware layers.
- Identify bottlenecks and apply dataflow, scheduling, quantization, and memory optimizations.
- Benchmark performance and collaborate across teams to ship improvements.
What they ask for
- B.S. in Computer Science, Electrical Engineering, or a related field.
- Strong programming skills in Python or C++; understanding of algorithms, data structures, and numerical computing.
- Experience with PyTorch, TensorFlow, or JAX, and with inference frameworks such as vLLM, TensorRT, or SGLang.
- GPU programming experience with CUDA or Triton.
Nice to have
- M.S. or Ph.D. in a related field; LLM training or inference experience.
- Familiarity with quantization, graph optimization, kernel fusion, model partitioning, memory hierarchy, caching, or scheduling; ML systems research or internship experience, publications, or open-source contributions.
Pay
$131,200 — $196,800 USD (base salary)
Tools
Python, C++, PyTorch, TensorFlow, JAX, vLLM, TensorRT, SGLang
AI focus
Foundation-model inference optimization, including quantization, kernel fusion, scheduling, and memory optimization.
Model-written summary · the original posting is authoritative