solutions architect for AI inference

Baseten; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Конкурентная компенсация

Значимая доля в компании

Медицинская страховка

Гибкий PTO

Родительский отпуск

401(k)

Опыт работы в ML-стартапах Baseten

Job summary

Baseten ищет опытного специалиста по работе с клиентами и технического лид-инициатора для работы с заказчиками в США. Вы будете вести демонстрации, определять требования и архитектурные подходы к развёртыванию, координировать POC и работать как связующее звено между Sales и Engineering.

Требуется глубокое понимание AI/ML и способность вести технические обсуждения без написания боевого кода. Условия включают конкурентную компенсацию, существенную долю, медицинскую страховку и гибкий PTO.

Qualifications

• Имеется опыт в AI/ML и уверенные разговоры на технические темы с стейкхолдерами.
• Сильные навыки коммуникации с клиентами и умение структурировать требования.
• Способность.scope решений без написания production-кода.
• Умение быстро prototyping скриптами в технических рабочих процессах.

Responsibilities

• Партнерство с отделом продаж на этапе discovery клиентов и демонстрациях.
• Проведение технических скопингов и определение критериев успеха, архитектуры и подхода к развёртыванию.
• Ведение бенчмаркинга и повторяемых развёртываний для моделей и других модальностей.

Skills

AI/ML background

customer-facing communication

technical depth

scripting/prototyping

benchmarking deployments

Tools

vLLM

SGLang

TRT-LLM

Job description

Описание: Baseten provides inference infrastructure and developer tooling that help AI companies bring cutting-edge models into production.

Задачи

• Partner with Sales on customer discovery calls, usually second calls and occasionally first calls for large accounts
• Lead demos and technical scoping to align on success criteria, architecture, and deployment approach
• Own benchmarking and repeatable deployments across LLMs, embeddings, image and video generation, Voice AI, and other modalities
• Advise on tradeoffs such as H100s versus B200s and latency-optimized versus throughput-optimized setups
• Drive playbook-style deployments for common models and use cases
• Become a power user of runtimes such as vLLM, SGLang, and TRT-LLM, including their configurations and tradeoffs
• Scope POCs and keep stakeholders aligned on timelines, deliverables, and next steps
• Coordinate POC execution as the project manager
• Bring in Forward Deployed Engineering support when deeper or more complex technical work is needed

Требования

• AI/ML background and the ability to discuss AI/ML topics credibly with technical stakeholders
• Strong customer-facing communication skills, including structured discovery and clarifying ambiguous requirements
• Technical depth to scope solutions without writing production code
• Ability to script and prototype as needed, including comfort with vibe coding in technical workflows
• Будет плюсом: experience running or supporting benchmarks for ML inference deployments, familiarity with infrastructure tradeoffs affecting inference performance and cost (such as GPU selection and latency versus throughput tuning), experience as a cross-functional technical lead for customer POCs coordinating Sales and Engineering

Условия

• Competitive compensation, including meaningful equity (U.S. only)
• 100% coverage of medical, dental, and vision insurance for the employee and dependents
• Flexible PTO policy, including a company-wide Winter Break; offices are closed from Christmas Eve to New Year's Day
• Paid parental leave
• Fertility and family-building stipend through Carrot (U.S. only)
• Company-facilitated 401(k)
• Exposure to a variety of ML startups, offering learning and networking opportunities