AI Engineer (Superhuman Mail) - US

Superhuman; United States; Remote; USD 150,000 - 220,000; Full time

Benefits offered by this job

Health care

Disability insurance

Life insurance

401(k) matching

Parental leave

Paid time off

Holidays

Floating holidays

Sick time

Home office stipend

Caregiving stipend

Wellness stipend

Dev budget

Job summary

Superhuman is seeking an AI Engineer on the Mail team to build the MCP, enabling agentic workflows and personalized AI experiences. You’ll work on backend systems and applied AI, selecting models and building the tools that empower agents to act for users.

You will collaborate across teams, ship features rapidly, and continuously improve how AI integrates with our products. This remote-friendly role offers flexibility and the chance to shape a rapidly evolving platform.

Qualifications

• 4–6+ years of software engineering with a strong backend foundation.
• Hands-on experience building and shipping LLM-powered features in production.
• Familiarity with MCP servers or tools, or eagerness to dive in.
• Working ML knowledge to reason about model selection and tradeoffs.

Responsibilities

• Build and evolve Superhuman Mail’s MCP: new tools, new standards, and new ways for agents to deliver 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
• Partner with teams across Superhuman to give them the AI building blocks they need
• Ship quickly while learning, and adjust course as the industry shifts
• (ML-leaning variant) Help shape our modeling approach, including what data to collect and how to generate it
• Technologies we use: Go, Postgres, Redis, Kubernetes, AWS, TurboPuffer

Skills

Backend development

LLM features

Eval systems

Model selection

Ownership

Growth mindset

AI enthusiasm

Tools

Postgres

Redis

Kubernetes

AWS

Go

Job description

Superhuman offers a remote-flexible working model for this particular role on the Mail team. This gives team members plenty of focus time and the flexibility to do their best work from wherever they’re based, while staying closely connected to a collaborative, tight-knit team culture. For those based in San Francisco, New York City, or Seattle, a hybrid setup is also available.

ABOUT SUPERHUMAN

Superhuman is the AI productivity platform on a mission to unlock the superhuman potential in everyone. The Superhuman suite of apps and agents brings AI wherever people work, integrating with over 1 million applications and websites. The company’s products include Grammarly’s writing assistance, Coda’s collaborative workspaces, Mail’s inbox management, and Go, the proactive AI assistant that understands context and delivers help automatically.

Founded in 2009, Superhuman empowers over 40 million people, 50,000 organizations, and 3,000 educational institutions worldwide to eliminate busywork and focus on what matters.

Learn more at superhuman.com http://superhuman.com and about our values here https://blog.superhuman.com/our-values/.

THE OPPORTUNITY

Superhuman is building the AI productivity platform that works everywhere people do, and Superhuman Mail is central to how people communicate and get work done. Today we are…The fastest email experience in the world - Loved and adored: see what our customers say https://superhuman.com/love.

On the Mail team, our AI Engineers build the platform behind our intelligent, agentic experiences, from the MCP layer that connects Superhuman to the tools people work in, to the personalization that makes the product feel like it knows you. This is engineering at the intersection of backend systems and applied AI. You’ll build the tools and standards that let agents take real action for users, and help teams across Superhuman ship AI features faster. We use many models, from OpenAI and Anthropic to open source, and a single feature like Ask AI can route across several depending on the task. You’ll help us find the best model for each job, no matter who built it. Superhuman’s engineers have the freedom to innovate and shape the product roadmap.

You can hear more from our team on our technical blog http://grammarly.com/blog/engineering.

AS AN AI ENGINEER, YOU WILL:

• Build and evolve Superhuman Mail’s MCP: new tools, new standards, and new ways for agents to deliver 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
• Partner with teams across Superhuman to give them the AI building blocks they need
• Ship quickly while learning, and adjust course as the industry shifts
• (ML-leaning variant) Help shape our modeling approach, including what data to collect and how to generate it
• Technologies we use: Go, Postgres, Redis, Kubernetes, AWS, TurboPuffer

QUALIFICATIONS

• 4-6+ years of software engineering experience 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
• Working ML knowledge to reason about model selection and tradeoffs. We’re looking for builders, not researchers
• Comfortable with ambiguity and quick changes in direction
• An AI enthusiast who uses AI to boost your own productivity and your team’s impact
• Strong ownership, a bias to action, and a growth mindset

COMPENSATION AND BENEFITS

• Excellent health care (including a wide range of medical, dental, vision, mental health, and fertility benefits)
• Disability and life insurance options
• 401(k) and RRSP matching
• Paid parental leave
• 20 days of paid time off per year, 12 days of paid holidays per year, two floating holidays per year, and flexible sick time
• Generous stipends (including those for caregiving, pet care, wellness, your home office, and more)
• Annual professional development budget and opportunities

Superhuman takes a market-based approach to compensation, which means base pay may vary depending on your location. Our US locations are categorized into two compensation zones based on proximity to our hub locations. Base pay may vary considerably depending on job-related knowledge, skills, and experience. The expected salary ranges for this position are outlined by compensation zone and may be modified in the future.

At Superhuman, we value our differences, and we encourage all—especially those whose identities are traditionally underrepresented in tech organizations—to apply. We do not discriminate on the basis of race, religion, color, gender expression or identity, sexual orientation, ancestry, national origin, citizenship, age, marital status, veteran status, disability status, political belief, or any other characteristic protected by law.

Superhuman is an equal opportunity employer and a participant in the US federal E-Verify program (US). We also abide by the Employment Equity Act (Canada).