# Solution Architect (AI/LLM Inference)

**Company:** [Baseten](https://hotfix.jobs/companies/baseten)
**Location:** San Francisco, CA, New York, NY
**Role:** Solutions Architecture
**Salary:** $165k – $330k/yr
**Skills:** AI/ML, LLMs, vLLM, Sglang, Trt-Llm, GPU, H100, B200, Embeddings, Inference, Benchmarks, Python, Scripting
**Posted:** 2026-05-10

> Partners with Sales to conduct technical discovery, lead demos, scope AI/LLM inference deployments, and manage POCs for customers adopting AI at scale. Requires AI/ML expertise, customer-facing skills, and ability to prototype solutions.

## Job Description

## Responsibilities
- Partner with Sales on customer discovery calls (most often second calls, 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, including:
  - Handling standard deployment patterns and configurations across many modalities – LLMs, embeddings, image and video generation, VoiceAI, etc.
  - Advising on tradeoffs like H100s vs B200s and latency-optimized vs throughput-optimized setups.
  - Driving consistent "playbook" style deployments for common models and use cases.
- Become a power user of different runtimes such as vllm, sglang, and TRT-LMM and all the common configurations and tradeoffs between them.
- Drive POC and project execution, including:
  - Scoping POCs and keeping stakeholders aligned on timeline, deliverables, and next steps.
  - Acting as the "ringleader" or project manager for POCs.
  - Pulling in Forward Deployed Engineering (FDE) support when deeper or more complex technical work is needed.

## Requirements
- AI/ML background and the ability to credibly discuss AI/ML topics with technical stakeholders.
- Strong customer-facing communication skills, including the ability to run structured discovery and clarify ambiguous requirements.
- Technical depth to scope solutions, without needing to write production code.
- Ability to script and prototype as needed, including comfort "vibe coding" to move quickly in technical workflows.

## Nice to Have
- Experience running or supporting benchmarks for ML inference deployments.
- Familiarity with infrastructure tradeoffs relevant to inference performance and cost (for example GPU selection and latency versus throughput tuning).
- Experience serving as a cross-functional technical lead for customer POCs, including coordination across Sales and Engineering.

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

## Similar roles

- [Data Cloud Architect, Analytics, Applied Field Engineering](https://hotfix.jobs/jobs/b6adda05-55f4-43e6-863f-5c5d4d17afc8) - Snowflake - Menlo Park, CA - $165k – $217k/yr
- [Forward Deployed Engineer](https://hotfix.jobs/jobs/57eb212c-5076-4980-b445-4d7a38aa3c5b) - Mattermost - Remote - $165k – $215k/yr
- [Data Platform Architect, Postgres](https://hotfix.jobs/jobs/c6635682-1b7b-48fb-95a8-bc9c508420a1) - Snowflake - Remote - $165k – $217k/yr
- [Deployed Engineer (Seattle)](https://hotfix.jobs/jobs/33e5c520-06a5-42fd-9675-818e60a6a257) - LangChain - Seattle, WA - $165k – $280k/yr
- [Cloud Partner Solutions Engineer (AWS / Azure / Google Cloud)](https://hotfix.jobs/jobs/75ee9193-0f72-4055-9cd5-9fb6528afa2b) - Snowflake - Remote - $165k – $217k/yr

**Apply:** https://hotfix.jobs/jobs/deb26ae5-887d-4e45-b845-6c7ca5e7f207
**Canonical:** https://hotfix.jobs/jobs/deb26ae5-887d-4e45-b845-6c7ca5e7f207