Software Engineer, Model Performance & HPC Tools

Baseten; New York (NY); On-site; USD 160,000 - 200,000; Full time

Benefits offered by this job

Competitive compensation with equity

100% medical, dental, and vision insurance coverage

Generous PTO including Winter Break

Paid parental leave

401(k) company-facilitated

Learning and networking opportunities

Job summary

A progressive AI company in New York is looking for early-career Software Engineers to enhance their AI infrastructure. In this role, you will engage in the intersection of high-performance computing and large language models, building tools to optimize performance benchmarks and ensure production readiness. Ideal candidates will possess a strong understanding of GPU systems and a passion for automation. The company offers competitive compensation with equity options and comprehensive health benefits.

Qualifications

• You should be curious about GPU memory subsystems and cluster data movement.
• An automation mindset is crucial for optimizing tasks.
• A desire to understand Transformers' math is essential.
• Interest in quantization and kernel-level optimizations is advantageous.

Responsibilities

• Run and automate LLM quality benchmarks and performance suites.
• Create automated acceptance tests for new GPU clusters.
• Develop and maintain GPU-enabled development environments.
• Build tools for model evaluation and optimization.
• Collect performance profiles and debug the NVIDIA stack.
• Develop dashboards to monitor system health and performance.
• Automate performance testing in CI/CD pipelines.
• Build tools for optimal configuration of models and workloads.

Skills

Understanding of GPU memory subsystems

Automation mindset

Mathematical curiosity

Interest in optimization

Familiarity with Python

C++ familiarity

Job description

A progressive AI company in New York is looking for early-career Software Engineers to enhance their AI infrastructure. In this role, you will engage in the intersection of high-performance computing and large language models, building tools to optimize performance benchmarks and ensure production readiness. Ideal candidates will possess a strong understanding of GPU systems and a passion for automation. The company offers competitive compensation with equity options and comprehensive health benefits.