Hi — we're Hypefy, a Croatian-based start-up.
We're building AI agents that run influencer marketing end-to-end: campaign creation, creator selection, outreach, content checks, payments, reporting — all automated, all at scale.
This isn't AI as a feature. It's AI as the core of how the product works. We want someone who's actually built production AI systems — not just experimented with them — and wants to push that further.
You'll design, build, and improve the AI systems that power the Hypefy platform — from the orchestration layer down to the prompt and model level.
Architect and maintain multi-step AI agent workflows for campaign automation, creator outreach, and content evaluation
Own the full reliability stack for AI features: structured outputs, schema validation, retries, fallbacks, and observability
Work with LLMs in production — prompt engineering, model selection, evaluation, iteration
Build pipelines for creator matching, content analysis, and automated decision-making
Integrate AI capabilities into existing backend systems (Node.js) without introducing fragility
Instrument and monitor AI systems — latency, accuracy, failure modes — and improve them continuously
Evaluate new models, tools, and approaches and bring the best ones into production
Small, senior-leaning engineering team
High ownership, low bureaucracy
You'll collaborate directly with product and founders
We use AI tools aggressively — in our product and in how we build it
Required
Experience building AI agent systems or LLM-powered features in production
Comfort with prompt engineering, evaluation, and iterative improvement
Strong software engineering fundamentals — this is an engineering role, not a research role
Experience handling the reliability challenges of LLM outputs: non-determinism, latency, structured output validation, fallbacks
Clear thinking about where AI adds value and where it creates risk
Comfortable working in Python
Nice to Have
Experience with orchestration frameworks (LangChain, LlamaIndex, or custom)
Experience with fine-tuning or embedding-based retrieval (RAG)
Background in NLP, content understanding, or classification tasks
Experience in SaaS, marketplaces, or automation-heavy platforms
Prior work integrating with Instagram, TikTok, or creator platforms
Comfortable working in Node.js
AI is central to the product — not a side project or an experiment
Real production systems with real users — you'll see the impact of your work immediately
Direct influence on how we use AI across the platform as we scale
A team that takes engineering quality seriously, even when moving fast