Agents Engineer
Technologies
prompt engineering · RAG · multi-agent architectures · model fine-tuning · Cursor · Windsurf · full-stack · AI IDEs · context engineering
About Flint
Flint helps growth teams generate and manage on-brand landing pages, comparison pages, and ABM microsites on their own domain without engineering bottlenecks.
Seed · 10–50 people
Job description
The full responsibilities and requirements are on the employer’s site.
Open application page ↗Source and classification
Production engineering · Evidence for this classification:
team's DNA. Because of that, our team knows how to catalyze hockey stick growth, but just as critically, how to navigate it sustainably to create $XB valued companies. After all, we've done it before. We are alums of Netflix, Scale, and Shepherd (YC W21), and work together in-person out of historic Jackson Square. The product Companies have used Flint to hit goals like… Ranking #1 on AI answer engines like ChatGPT, Perplexity and Google AI Overview Lifting ad conversion rates Generating hundreds of thousands of dollars in pipeline revenue What you'll own The agentic systems behind Flint's core product: reliability, capability, observability. The central problem of the role is making them hold up in production, not just in demos. The pipeline that ingests customer websites and extracts brand signals for generation. Multi-agent architectures that survive real traffic and edge
More from the job description
About Flint Flint is the agentic platform that ships pages from your brand and ad campaigns. AI doesn't replace marketers. It removes the work that should never have been theirs: building a one-off landing page for every keyword, every campaign change, every A/B test, then waiting on design and engineering to do it. Today we deliver on-brand pages on your own domain in minutes, with no rebuilds and no engineers. We're backed by Accel, Sheryl Sandberg (former Meta COO)'s venture fund SBVP, and Neo. The vision Sandberg instantly understood Flint's vision. "I was sharing how it took (me) five teams three months to build one A/B test just to increase conversion by 10% on our Google ad," Lim said. "And then she stopped me, [and] said, 'Michelle, it was 140 people at Meta who had to do this'." — TechCrunch Imagine a website that builds new pages, tests creative, and optimizes performance in response to real-world signals: competitive shifts, user behavior, trending search queries, the way an autonomous vehicle responds to road conditions and traffic. The marketer still owns the work that compounds and the work that requires taste: strategy, audience, creative direction, brand judgment. Flint takes the manual production off their plate so they get those hours back. The team "One of the most talent-dense AI startups... each member of the early Flint team has a track record, and as a [... source excerpt omitted ...] Ranking #1 on AI answer engines like ChatGPT, Perplexity and Google AI Overview Lifting ad conversion rates Generating hundreds of thousands of dollars in pipeline revenue What you'll own The agentic systems behind Flint's core product: reliability, capability, observability. The central problem of the role is making them hold up in production, not just in demos. The pipeline that ingests customer websites and extracts brand signals for generation. Multi-agent architectures that survive real traffic and edge cases. Evals and testing for agentic systems. Integrating agent capabilities into the broader platform alongside product engineers. You're a fit if You've built p [... source excerpt omitted ...] duction agent systems you can point to. You have deep hands-on experience with prompt engineering, context optimization, and multi-agent orchestration. You've debugged agents in production and know how to make them predictable at scale. You've got a strong full-stack foundation, agents don't live in isolation. Bonus You've applied AI to design systems, brand generation, or code generation. You know website builders (Webflow, Framer) or CMS platforms (Sanity, Contentful). You've built RAG systems or fine-tuned a model for a specific domain. Flint in the press TechCrunch - Oct 2025 Business Insider - Nov 2025 Pragmatic Engineer podcast - Dec 2025 CNBC - Dec 2025 Follow u
Employer postings · Data from · Sources