Sobre nBlick
nBlick es una plataforma de visibilidad en IA. Medimos cómo ChatGPT, Claude, Gemini, Perplexity y otros asistentes describen y recomiendan una marca: ejecutamos prompts por persona en más de 10 modelos cada día y convertimos cada respuesta en métricas estructuradas como tasa de mención, share of voice y sentimiento. La búsqueda se está convirtiendo en respuestas, y construimos las herramientas para que las marcas vean y cambien cómo aparecen allí.
Sobre el puesto
Build the core intelligence behind nBlick. You'll design and run the systems that query AI models at scale, extract structured brand data from unstructured responses, and turn raw model outputs into actionable signals.
What you'll do
- Design and maintain pipelines that run thousands of LLM queries daily across multiple models
- Extract structured insights (brand mentions, sentiment, competitor comparisons) from model outputs
- Develop and iterate on evaluation frameworks to measure AI response quality
- Research emerging AI models and integrate them into our tracking infrastructure
- Collaborate with product to turn model data into user-facing insights
What we're looking for
- Strong hands-on experience with LLM APIs (OpenAI, Anthropic, Google, etc.)
- Comfortable building and scaling data pipelines in Python
- Good judgment on when to prompt-engineer vs. fine-tune vs. use structured outputs
- Experience with async systems and managing API rate limits at scale
- Bonus: experience with NLP evaluation, benchmarking, or RAG systems