Senior Applied AI Engineer — Production Agent Systems

Aimlroles; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity stake

Health plan

Generous PTO

Gym budget

Lunch

Job summary

Sauna by Wordware is seeking a Senior Applied AI Engineer in San Francisco to own and scale agent systems—from architecture to deployment. You’ll ensure fast responses, reliability, and traceability for production workloads and directly influence how the team builds agents.

You should have shipped agent systems in production, with strong emphasis on memory, orchestration, and tool usage. This is a hands-on, high-ownership role in a tight-knit team.

Qualifications

• You've built and deployed agent-like systems: multi-step LLM pipelines, tool-using bots, scripted assistants, or similar.
• You ran at least one of them in production, made the architecture calls on it, and can explain the tradeoffs.
• Hands-on experience with agent orchestration and memory management, tool use and orchestration, and evaluation.
• You write production-grade code and can work across systems without needing a spec.
• You'd rather ship than polish forever.

Responsibilities

• Build, refine, and scale the agent systems inside Sauna, from architecture to evals to deployment.
• Ensure production readiness: fast response times, predictable behavior, traceability, and uptime.
• Make architectural calls on real agent systems and justify decisions.
• Collaborate across infra, frontend, and product to ensure agents work as intended.

Skills

Agent orchestration

Memory management

Tool use and orchestration

Production-grade code

Architecture decisions

Code review

Proactive problem solving

Tools

APIs & plugins

Auth flows

LLM tooling

Job description

Sauna by Wordware is seeking a Senior Applied AI Engineer in San Francisco to own and scale agent systems—from architecture to deployment. You’ll ensure fast responses, reliability, and traceability for production workloads and directly influence how the team builds agents.

You should have shipped agent systems in production, with strong emphasis on memory, orchestration, and tool usage. This is a hands-on, high-ownership role in a tight-knit team.