Senior Software Engineer, Model Performance & HPC

Baseten; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity

Medical/dental/vision for US employees

Flexible PTO including winter break

Job summary

Baseten in San Francisco is seeking software engineers at the intersection of high-performance computing and large language model engineering. You will define the roadmap, drive key technical decisions, and take full ownership of the future of our model-inference tooling.

Join a small team building GPU-optimized development environments, open-source tools, and real-time dashboards to push the boundaries of AI infrastructure. This mid-senior role rewards ownership and cross-team collaboration.

Qualifications

• Love for systems & hardware and GPU memory subsystems knowledge.
• Automation mindset with stress-testing and fuzzy testing.
• Curiosity about Transformers math and FLOPs/memory implications.
• Proficiency with Python and NVIDIA software stack; C++ familiarity helps.

Responsibilities

• Benchmark LLM quality benchmarks (GSM8K, MMLU) and custom performance suites.
• Develop GPU-enabled development environments (like Codespaces) for model experimentation.
• Build/open-source tools to automate model evaluation and benchmarking (e.g., InferenceMAX, genai-bench).
• Use profilers to collect performance profiles and debug compute/networking stacks.
• Create real-time dashboards and alerts for system health and startup times.
• Automate CI/CD performance testing and release workflows for model runtimes.
• Identify Pareto frontier configurations for latency, cost and quality.

Skills

Systems & Hardware

Automation Mindset

Mathematical Curiosity

Technical Toolkit

Tools

Python

NVIDIA software stack

C++ familiarity

Job description

Baseten in San Francisco is seeking software engineers at the intersection of high-performance computing and large language model engineering. You will define the roadmap, drive key technical decisions, and take full ownership of the future of our model-inference tooling.

Join a small team building GPU-optimized development environments, open-source tools, and real-time dashboards to push the boundaries of AI infrastructure. This mid-senior role rewards ownership and cross-team collaboration.