Software Engineer, Platform Experience - Siena

Meet Siena

Siena is the Agent of Record for CX, built for consumer brands like Spanx, FIGS, Brooklinen, and Grüns.

It runs as a connected multi-agent stack on top of a shared intelligence layer: agents that sell, support, listen, handle social and voice across the entire customer journey, turning every conversation into signal you can act on.

The Team

We are a small, fully distributed, global team. We have built leverage into how we work, which is what lets a team this size move at the speed we do.

We hire athletes. Everyone here owns real outcomes, defaults to writing over meetings, communicates with directness, and acts the moment they see something worth acting on. Low ego, high standards, fast clock.

If you want to set the bar rather than follow one, keep reading.

The Role

You take the hardest problems our customers hit in production and solve them end to end. A webhook that stopped firing overnight. An agent filling the wrong parameter. A report that won't reconcile. Today those land on a product engineer's desk and pull them off the roadmap. That stops with you.

• More than troubleshooting: You find the real cause, work with the customer directly to a resolution (including jumping on a call when that's fastest), then build the automation so it never comes back.
• You're an accelerator: Every fix makes the next one faster and the product better.
• A clear path forward: This is the front door to deployment and platform work at Siena. Grow from here into a Forward Deployed Engineer or deeper into platform engineering.

Who You Are

• You solve problems end to end: Given a customer, some logs, and a vague symptom, you find the break and tell a customer-side cause from a product bug. You don't stop at "it's not our bug."
• You like talking to customers: You'll get on a call, find the real problem behind the report, and resolve it live. Customer contact is leverage, not a chore.
• You're excited to build automation: The fix in front of you is half the job. Building the thing that means nobody fixes it again is the other half. You think in leverage.
• You're fluent with AI agents and prompts: You've built or debugged LLM workflows and know how they break: prompts, knowledge bases, intent classification, retrieval, and the gap between what passes in test and what runs live. You can read a prompt, spot why it misfires, and rewrite it.
• You read and reason through code: You're comfortable in our core stack—Node.js, TypeScript, React, Express—or close enough to ramp fast. You can trace customer-side JavaScript in the browser, write diagnostic SQL against PostgreSQL, and navigate a backend service independently.
• You use AI coding tools as leverage: Fluent with Claude Code or equivalent to script a query, clean a dataset, or navigate a new codebase fast.
• You own problems nobody assigned you: You've worked where the process didn't exist yet, found something broken, and driven it to a fix.
• You make people around you better: You leave teammates more capable through docs, tools, and walkthroughs.
• Nice to have: Observability tooling (Grafana, Honeycomb, Sentry); internal tooling that turned manual work into a system. Ecommerce or DTC exposure is a plus.

What You'll Do

• Own the hard problems end to end: Trace, reproduce, fix, or hand engineering a clean reproduction. Range across APIs and integrations, customer-side JavaScript, agent behavior, and data.
• Debug the agents and the prompts: Diagnose whether a wrong answer or misfire is prompt, knowledge base, config, or model, then fix the prompt or setup so it holds under real traffic.
• Build so it doesn't happen twice: For every fix, ensure the team can handle this next time with a runbook or tool, and build systems to catch the next occurrence automatically.
• Close the loop to Product: Act as the structured, metrics-backed signal between what customers hit in the wild and what we build next. Surface patterns, not one-offs.
• Raise the team's floor: Lift what the whole team can resolve instead of being the single point of failure.
• Know where your scope ends: Escalate genuine product bugs, infrastructure issues, and outages with a clean reproduction.

Why Siena?

• Real ownership: Own problems, not tasks, with the autonomy to solve them your way.
• Work that ships and matters: What you build reaches real consumer brands fast.
• A category we are creating: The Agent of Record is new ground with unsolved problems and cutting-edge models.
• A team that respects your judgment: Globally distributed, async-first, low bureaucracy.
• Great salary plus equity or stock grants: Own a piece of what you build.
• Learning budget: Dedicated budget to support your professional growth.
• AI-fluency by default: Access to premium accounts (ChatGPT, Claude, Perplexity Pro, Cursor, Lovable) plus a quarterly budget for new tools.