Remote AI Engineer — Backend, Agents & Personalization

Superhuman; San Francisco (CA); Remote; USD 154,000 - 257,000; Full time

Benefits offered by this job

Excellent health care

Disability and life insurance options

401(k) matching

Paid parental leave

PTO & holidays

Floating holidays

Flexible sick time

Stipends for caregiving, home office,–

Professional development budget

Job summary

Superhuman is seeking an AI Engineer for the Mail team to advance our AI-powered inbox experiences. You will work at the intersection of backend systems and applied AI, building tools and standards for agents to deliver value and shaping how we ship AI features at scale.

You will evaluate models, select appropriate ones, and collaborate with teams to provide AI building blocks while adapting to industry shifts and new data approaches.

Qualifications

• 4-7+ years of software engineering with a strong backend foundation (Python or TypeScript is great, Go is a plus).
• Hands-on experience building and shipping LLM-powered features in production, such as agents or agentic loops.
• Experience building evals to measure and improve LLM quality.
• Familiarity with MCP servers or tools, or eagerness to dive in.

Responsibilities

• Build and evolve Superhuman Mail's MCP: new tools, standards, and agent delivery value to end users.
• Design and ship agentic workflows and personalization features at scale.
• Build evaluation systems that measure quality and catch regressions as prompts, models, and tools change.
• Help choose the right models for each task and keep exploring new ones.

Skills

Backend experience

Python/TypeScript

Go

LLM features

Model evals

MCP servers

ML knowledge

Ownership mindset

Tools

Go

PostgreSQL

Redis

Kubernetes

AWS

Job description

Superhuman is seeking an AI Engineer for the Mail team to advance our AI-powered inbox experiences. You will work at the intersection of backend systems and applied AI, building tools and standards for agents to deliver value and shaping how we ship AI features at scale.

You will evaluate models, select appropriate ones, and collaborate with teams to provide AI building blocks while adapting to industry shifts and new data approaches.