Postúlate en Kit Empleo: kitempleo.pe/empleo/wkkto

Role overview

nWe are hiring an AI-native, full-stack engineer to design, ship, and scale production-grade applications powered by large language models (LLMs), generative AI, and workflow automation. You will own features end-to-end across web, mobile, and backend services, and you will use n8n and similar tools to glue internal systems, third- party APIs, and AI models together into reliable, observable workflows. The idóneo candidate treats LLMs as a core part of their engineering loop, has strong opinions about model selection and prompt design, and is fluent across the modern JavaScript/TypeScript stack, the Google Cloud ecosystem, and modern automation platforms.n

The Tech Stack

n

Category Our Ecosystem

nFrontend: Next.js, TypeScript, Tailwind CSSn

Mobile: React Native (Expo/CLI)

nBackend: Node.js (NestJS or Fastify preferred)n

Cloud/Data: Google Cloud Platform (GCP), BigQuery

n

AI Infrastructure: Vertex AI, Gemini API, Anthropic/OpenAI SDKs

n

What You’ll Do

n

n
- Architect Intelligent Apps: Build and maintain full-stack applications that leverage LLMs (Claude, Gemini, GPT-4) to provide real-world value.
n
- AI-Driven Development: Utilize modern AI coding tools (Cursor, Copilot, etc.) to maintain a high velocity without sacrificing code quality.
n
- Data Orchestration: Interface with Google BigQuery to feed structured data into Vertex AI pipelines for custom model tuning or RAG (Retrieval-Augmented Generation) workflows.
n
- Cross-Platform Delivery:



Maintain a unified experience between a high-performance Next.js web app and a robust React Native mobile application.
n
- Prompt Engineering & Fine-tuning: Move beyond simple API calls; optimize system prompts and evaluate model outputs to ensure production-grade reliability.
n

nWho You Are

n
- An AI Power User: You have a deep workflow involving Anthropic, Gemini, or OpenAI. You know which model excels at which task.
n
- GCP Savvy: You’re comfortable navigating the Google Cloud ecosystem, specifically managing datasets in BigQuery and deploying models via Vertex AI.
n
- Full-Stack Fluency: You can jump from a TypeScript frontend component to a Node.js microservice without breaking a sweat.
n
- Efficiency Obsessed: You don't believe in "doing it the hard way" if a tool can do it better. You value shipping high-quality products over writing "manual" boilerplate.
n

nNice to Have:n

n
- Experience with orchestration frameworks such as LangChain, LlamaIndex, or LangGraph.
n
- Production experience with vector databases (pgvector, Pinecone, Weaviate, Qdrant, or similar) and hybrid search.
n
- Experience fine-tuning models or building robust evaluation harnesses for LLM outputs.
n
- Experience writing custom n8n nodes, contributing to the n8n community, or running n8n at scale (queue mode, worker scaling, observability).
n

nPregunta(s) de postulación:nn
- Pretensiones Salariales Soles
n

nIdioma:nn
- Ingles (Obligatorio)
n

nLugar de trabajo: Empleo remoto

Postúlate en Kit Empleo: kitempleo.pe/empleo/wkkto

📌 Full-Stack AI Engineer (Lima)
🏢 Align Peru
📍 Lima