AI-Native Product Engineer

Cyclotron, Inc.•Chicago, IL

2d•$120,000 - $149,999•Remote

About The Position

We are seeking a rare hybrid profile: a senior, product-minded, AI-native engineer who can own a product area end-to-end, from a vague business objective through thoughtful product definition, technical design, implementation, testing, and iteration. This person should operate less like a ticket-based contractor and more like a founding engineer assigned to a product area. The ideal candidate can understand user needs, define effective workflows, make sound SaaS architecture decisions, use AI tools to accelerate high-quality development, validate and test generated code, communicate clearly, and move work forward independently in ambiguous environments.

Requirements

Senior-level engineering experience with the ability to design, build, validate, and improve production software.
Strong product judgment, including the ability to understand users, workflows, pain points, business outcomes, and success criteria.
Demonstrated ability to operate in ambiguity, ask clarifying questions, challenge assumptions respectfully, and make progress without highly detailed tickets.
Advanced fluency with AI-assisted development tools such as Cursor, Claude, ChatGPT, GitHub Copilot, or similar environments.
Ability to orchestrate AI tools effectively rather than treating them as simple autocomplete or boilerplate generators.
Strong technical judgment across SaaS architecture, including data modeling, API design, frontend and backend design, permissions, integrations, scalability, error handling, maintainability, and security considerations.
Solid understanding of modern SaaS UX patterns and the ability to build interfaces that feel intuitive, polished, and product-quality.
Excellent written communication skills, with the ability to explain reasoning, tradeoffs, risks, blockers, and decisions clearly and concisely.
Ownership mindset with the ability to act as a force multiplier for the product and engineering organization.

Nice To Haves

Ability to define product workflows, key screens, data models, permissions models, user actions, edge cases, and implementation approaches from vague product goals.
Experience using AI for code generation, architecture comparison, debugging, refactoring, test creation, documentation, and rapid iteration.
Ability to identify hallucinations, flawed logic, architectural gaps, and quality issues in AI-generated output.
Strong instincts around SaaS admin workflows, multi-tenant considerations, auditability, notifications, readiness tracking, executive summaries, and operational dashboards.
Comfort evaluating tradeoffs between MVP scope, future scale, usability, performance, security, and maintainability.
Ability to communicate asynchronously with clarity, structure, and appropriate context for technical and non-technical stakeholders.
Strong candidates will show evidence of owning product, UX, architecture, and implementation together, rather than operating only as a backend, frontend, or ticket-based individual contributor.
This role is not a fit for someone who requires fully defined requirements, avoids ambiguity, cannot explain architectural decisions, has weak written communication, or cannot use AI tools at an advanced level.

Responsibilities

Own product areas from broad business goals through discovery, design, implementation, testing, and iteration.
Translate ambiguous objectives into clear user workflows, product requirements, technical plans, and implementation steps.
Question unclear requirements, identify missing pieces, surface risks and edge cases, and propose better product or technical approaches when appropriate.
Design and build polished, intuitive SaaS workflows, including dashboards, tables, filters, forms, detail views, configuration experiences, empty states, loading states, and error states.
Make thoughtful architecture decisions across data models, APIs, frontend architecture, backend architecture, permissions, integrations, state management, scalability, security, and maintainability.
Use AI-assisted development tools to accelerate coding, refactoring, debugging, test creation, documentation, and architectural exploration.
Critically review, validate, debug, and test AI-generated code to ensure production-quality implementation.
Communicate clearly and proactively about requirements, architecture, tradeoffs, implementation status, open questions, risks, and blockers.
Drive work forward independently while collaborating effectively with product, engineering, design, and business stakeholders.