Software Engineer, LLM Performance & Systems

Baseten; Seattle (WA); Presencial; USD 165 000 - 330 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Competitive compensation & equity

US medical/dental/vision insurance for

flexible PTO including Winter Break

Paid parental leave

Fertility and family-building stipend

401(k)

Resumo da oferta

Baseten is seeking software engineers to join our HPC/LLM-focused team. You will shape the roadmap, drive key technical decisions, and own critical infrastructure that powers next-generation AI models in production.

This mid-senior role blends systems, hardware awareness, and automation. You will build high-performance dev environments, contribute to open-source tools like InferenceMAX and genai-bench, and mentor other engineers while shipping reliable, scalable software.

Qualificações

• Mid-senior level with high impact responsibilities.
• Strong communication and cross-team collaboration.
• Ability to mentor other engineers.
• Experience with GPUs and HPC concepts.

Responsabilidades

• Benchmark LLM quality and performance benchmarks (GSM8K, MMLU) and workload-specific tests.
• Develop and maintain GPU-enabled development environments like Codespaces.
• Build and contribute to open-source tools to automate model evaluation and benchmarking.
• Use profilers to collect performance profiles and debug compute/networking stacks.
• Develop real-time dashboards and alerts for system health and runtime performance.
• Automate CI/CD performance testing and release workflow for model runtimes.
• Identify Pareto-optimal configurations for latency, cost, and quality.

Conhecimentos

Systems & hardware

Automation mindset

Mathematical curiosity

Python

C++

NVIDIA software stack

Ferramentas

GitHub Codespaces

InferenceMAX

genai-bench

PyTorch Profiler

NVIDIA Nsight Systems

py-spy

Descrição da oferta de emprego

Baseten is seeking software engineers to join our HPC/LLM-focused team. You will shape the roadmap, drive key technical decisions, and own critical infrastructure that powers next-generation AI models in production.

This mid-senior role blends systems, hardware awareness, and automation. You will build high-performance dev environments, contribute to open-source tools like InferenceMAX and genai-bench, and mentor other engineers while shipping reliable, scalable software.