Baseten
Baseten
Baseten provides model inference infrastructure for companies deploying machine learning and AI applications. Its platform is built for fast, scalable serving, combining high-throughput inference, rapid deployment, autoscaling, secure enterprise model serving, and support for open-source model packaging. Baseten helps engineering and machine learning teams manage the operational demands of model infrastructure so they can focus on developing domain-specific models. The company operates across artificial intelligence, SaaS, and enterprise technology, with a team of 11–50 employees.

Solutions Architect – AI/ML Inference, Remote United States

Join Baseten as a Solutions Architect helping customers turn AI/ML requirements into production-ready inference deployments and proofs of concept. Work with Sales and Engineering on discovery, demos, benchmarking, architecture, and technical delivery.

Description

  • Collaborate with Sales during customer discovery calls
  • Lead demonstrations and technical scoping around success criteria, architecture, and deployment plans
  • Own benchmarking and repeatable deployments for LLMs, embeddings, image and video generation, and Voice AI
  • Guide customers through GPU and inference configuration choices, including H100 versus B200 selection and latency-versus-throughput optimization
  • Develop repeatable deployment playbooks for common models and use cases
  • Build deep practical expertise in vLLM, SGLang, TRT-LLM, and their typical configurations and tradeoffs
  • Define proofs of concept and coordinate stakeholders on timelines, deliverables, and next steps
  • Manage customer proofs of concept as the technical project lead
  • Engage Forward Deployed Engineering when projects require deeper or more complex technical support

Requirements

  • Background in AI/ML with the credibility to discuss technical topics with customer stakeholders
  • Strong customer-facing communication skills, including structured discovery and the ability to resolve ambiguous requirements
  • Technical expertise sufficient to scope solutions without writing production code
  • Ability to script and prototype when needed, with comfort using rapid coding workflows
  • Experience conducting or supporting benchmarks for machine learning inference deployments
  • Understanding of infrastructure decisions affecting inference performance and cost, including GPU selection and latency-versus-throughput tuning
  • Experience leading customer proofs of concept across Sales and Engineering as a cross-functional technical owner

Benefits

  • Competitive compensation with meaningful equity
  • For U.S. employees and dependents, full medical, dental, and vision insurance coverage
  • Flexible paid time off with a company-wide Winter Break
  • Paid parental leave
  • Fertility and family-building stipend through Carrot
  • For U.S. employees, a company-facilitated 401(k) plan
  • Opportunities to work with diverse ML startups and expand learning and professional networks

Related Jobs

ReSus Consult GmbH

Sales Director, HVAC and Plumbing (SHK)

ReSus Consult GmbH
DEGermany
€120,000 – €180,000 / year
HybridFull-timeLeadGerman RequiredSales

Lead a regional portfolio of five to twelve SHK trade businesses, with responsibility for budgets and operational development. Build regional collaboration through digitalization, shared capacity, larger projects and best-practice exchange.

Open
smartkündigen OHG

Senior Sales Manager (German-speaking), Remote

smartkündigen OHG
11 – 50 Employees
B2CProductivitySaaS

Advise customers, grow existing accounts, and close sales for smartkündigen’s digital contract cancellation service. Work fully remotely without cold calling.

Open
smartkündigen OHG

Senior Sales Manager, Remote

smartkündigen OHG
11 – 50 Employees
B2CProductivitySaaS

Advise customers, grow existing accounts, and close sales for smartkündigen’s digital contract cancellation service. Work fully remotely worldwide, handling inbound inquiries without cold calling.

Open