Town.com, Inc.
Backend Engineer
- Location
- New York City, NY, US
- Arrangement
- On-site
- Employment type
- Full-time
- Posted
- 23 July 2026 (about 2 months ago)
Checked 15 days agoApplications go to the employer, never to RoleSprint
About this role
ABOUT TOWN
Town is an AI-powered assistant that connects to your tools to do real work on your behalf -- triaging your inbox, drafting in your voice, managing your schedule, and running workflows across everything you use. It knows you deeply and gets sharper over time.
ABOUT THE ROLE
The core technical challenge at Town is: context from everywhere, action anywhere. The assistant pulls from your email, calendar, Slack, docs, and connected tools to build a deep understanding of who you are and what you need -- then executes reliably across all of them.
Town's AI assistant goes beyond a solid harness and decent tool integrations. It has memory that compounds over time, a suggestion engine that discovers what to automate before you think to ask, and network effects where your assistant gets better because your colleagues are using Town too. These are the systems you'll build.
You'll be a foundational hire, working across the full backend -- from LLM orchestration and workflow execution to the identity and knowledge layer that makes every interaction smarter than the last. Everyone has direct influence over architecture decisions. There's no platform team to hand things off to -- you own it end to end. The environment is greenfield, and the problems are unlike traditional backend engineering: non-deterministic, cost-sensitive LLM workloads; real-time personalization across a growing knowledge graph; agent-to-agent protocols that work across organizational boundaries.
EXAMPLE PROJECTS INCLUDE...
- Building the orchestration layer for agentic workflows
- Building multi-provider LLM infrastructure
- Rethinking email, calendar, and contacts as AI-native experiences
- Designing the identity and knowledge layer
- Architecting agent networks
- Building the trust and autonomy system
- Defining what service ownership
YOU MIGHT THRIVE IN THIS ROLE IF YOU...
- Have built and scaled backend systems through a company's high-growth arc -- you were there during the inflection, not after. We want to hear all your your concrete product scaling stories.
- Are comfortable defining technical direction in ambiguous, fast-moving environments -- not just executing within one
- Think in systems -- distributed systems, data pipelines, APIs, reliability. You're drawn to infrastructure-level problems and the tradeoffs that come with them.
- Have tuned your AI-native coding workflow that makes you dramatically faster and more effective.
- Have experience with LLM infrastructure, agentic systems, or real-time AI workloads in production
- Care about trajectory over tenure. We're less interested in years of experience than how fast you got here and what you built along the way.
- Are excited about working in-person, five days a week. We believe it matters at this stage.
LOCATION
5 days per week in person, in either SF or NYC
Work location
- New York City, NY, US
Related jobs
Ready to make a decision?
This role is either worth your time or it isn’t.
Analyze the posting against your experience, see the gaps clearly, and build the right materials only if the opportunity makes sense.
Nothing is submitted automatically. You choose what happens next.
About this listing
Published on Ashby under the board identifier Town, which is the name the employer’s own job board carries. RoleSprint has not verified the company’s registered or trading name, so it is shown exactly as published rather than tidied up.
RoleSprint is not the employer and not a recruiter. Applications are made on the employer’s own site and never reach us; what RoleSprint does is help you decide whether a role is worth your time and prepare for it if it is.
Published 23 July 2026, last checked 15 days ago. A posting stops being advertised here 90 days after the employer published it, and one the employer takes down is marked closed rather than quietly removed.