About the Role

Sonic is Propel's AI-native marketing platform. It pairs a chat-based agent with each marketer's brand, content, and the data sitting inside their existing marketing stack — campaign tools, product analytics, knowledge bases, communication channels — so they can move from a campaign brief to a live, executed campaign with fewer iterations and higher-quality output.

As Senior AI Product Engineer at Propel, you are the architect on Sonic's platform — the engineer who designs the multi-tenant data model, the APIs, the seams between the agent and the surface the marketer sees, and the patterns the team builds on. You spend roughly 70% of your time on the backend and 30% on the frontend, wiring designer specifications into shipped features.

The coding itself is largely done with AI agents (Claude and equivalents). What we hire you for is judgement — the ability to see the right shape of a system before others do, and the ability to write a specification sharp enough that the next engineer or an AI agent builds the right thing without you in the room.

You will own how the platform behaves in production. You do not need to have worked on AI products before. You need to have built robust, multi-tenant SaaS that scaled.

Key Responsibilities

Architect the multi-tenant foundation of Sonic — tenant isolation, organization-scoped data, role based access, per-tenant quotas — and write the patterns down so the rest of the team builds to them.
Own the backend that powers the conversational experience — streaming agent responses, artifact persistence, file handling, real-time state, conversation history, and tool-call execution.
Design the seams between backend and frontend — the APIs, data models, and contracts that the frontend implementation builds on — and wire the frontend yourself for the 30% of your time that lives there. ‍
Translate the designer's UX specifications into shipped features end-to-end. Make the platform behave the way it's supposed to in production, every time. ‍
Architect features as new product direction is sequenced — schemas, APIs, data flow, async patterns, the seams that hold the system together as it grows. ‍
Author RFCs (Request for Comments) end-to-end — written design documents that specify the problem, alternatives considered, trade-offs, the decision, and what is explicitly not being built. Sharp enough that another engineer or an AI agent could build the right thing without you in the room. ‍
Set the technical bar across engineering — review others' work, raise the architectural standard, and informally mentor peers. There is no formal authority over peers; mentorship is earned, not granted. ‍
Ship through AI agents. Write specifications Claude (or equivalent) can execute against, review the output critically, and ship the result. Propel engineers do not measure their value in lines of code typed. ‍
Collaborate closely with the designer — translate UX specifications into engineering specs, and surface ambiguities back to the designer rather than resolving them on your own. ‍
Collaborate closely with the engineers who build on top of your platform, shaping the API surface to match how the agent actually consumes it.

Required Competencies

3–5 years of total engineering experience.
At least 2 years on multi-tenant SaaS at production scale. You have shipped a B2B SaaS product that served multiple paying organizations, and you understand viscerally why multi-tenancy is hard. Backend-heavy full-stack. You can architect a backend system and wire a React frontend. Not necessarily 50 / 50 — 70 / 30 backend / frontend is the expected split.
Strong foundation in systems design — schema design, API design, async patterns, queues, real-time / streaming, caching, consistency trade-offs. Opinions on these, and the ability to defend them in front of a senior peer.
Strong technical competency in our stack: TypeScript, Node.js, PostgreSQL with Drizzle ORM, and React. Production experience required.
AI-augmented engineering as a first-class part of your loop. If working through Claude (or equivalent) feels uncomfortable to you, this role is not a fit.
Written communication strong enough to author RFCs that an AI agent or a junior engineer can build from without you in the room.
Smart and curious — first-principles reasoning, comfortable in ambiguity, learns the next thing fast

Bonus: experience with chat UI, artifact rendering, streaming agent responses, or similar real-time surfaces; experience designing APIs that a retrieval or context layer plugs into; has worked closely with a designer as a peer collaborator; has mentored a junior engineer to ship-readiness; startup-scale experience (Seed–Series B); LLM, agent, or AI feature experience (not weighted heavily — but if you have it, mention it).

How We Measure Performance

Performance at Propel is measured on a written, six-axis rubric. Every engineer is evaluated on the same axes — what changes between levels is the bar, not the rubric itself. For this role, we weight axis 3 (System & architectural thinking) most heavily.

The six axes:

Problem framing & specification — Can you describe what we should build, what we should explicitly not build, and why?
Engineering judgement & verification — Do you instrument before you ship? Do you catch regressions before users do?
System & architectural thinking — Can you reason about the system as a whole, not just the feature you're building?
Product thinking & user affinity — Do you understand why the marketer cares about what you ship? 5. Ownership & delivery — When you say you own something, do you mean it end-to-end?
Collaboration & communication — Can your written work survive contact with a fresh engineer, an AI agent, or a designer who joined this week?

Each axis is scored on a 1–5 scale.

Review cadence:

A written six-month checkpoint — lightweight re-score, no CTC change, feedback on which axes need to move and how.
A full re-score at twelve months — compensation recalibrated as scope expands and as the team grows under your architectural direction.

Performance bonus:‍

Up to 20% of fixed CTC, paid annually after the 12-month review, conditional on a small set of named outcomes agreed at the start of the role. If the bar is hit, the bonus pays. If it is not, the bonus does not pay. There are no surprises in either direction.

What You Get

Total target compensation between ₹30–42 LPA — fixed base plus performance bonus, anchored to our AI-native compensation framework.
Compensation recalibrated annually based on rubric trajectory and the scope you take on as the team grows.
Meaningful equity at founding-team scale, discussed at offer stage.
A small, intentionally lean team where AI-augmented engineering is the operating model, not a buzzword.
A written performance framework — the same rubric for everyone, a six-month checkpoint, a twelve month re-score, no surprises.