Full-Stack AI Engineer (LLMs, AI Products & Full-Stack Development)
Position Type: Full-Time, Remote
Working Hours: U.S. Business Hours
About the Role
At Pavago, one of our clients is hiring a Full-Stack AI Engineer to build and deploy production-ready AI-powered applications.
This role combines full-stack software engineering with applied AI to deliver scalable, secure, and user-friendly products. You’ll work across backend systems, frontend applications, AI pipelines, APIs, vector databases, and cloud infrastructure to transform AI prototypes into real-world solutions.
ResponsibilitiesAI & LLM Development
Build and deploy AI-powered applications using OpenAI, Hugging Face, PyTorch, TensorFlow, or similar technologies.
Develop scalable AI inference APIs with FastAPI, Flask, or Node.js.
Build AI assistants, chatbots, copilots, and intelligent workflows.
Implement embeddings, vector search, RAG pipelines, and semantic retrieval using Pinecone, Weaviate, FAISS, or similar platforms.
Full-Stack Development
Develop frontend applications using React, Next.js, Vue, or similar frameworks.
Build backend services, APIs, and microservices that integrate AI with business logic.
Deliver responsive, scalable, and production-ready AI experiences.
Data Engineering & Infrastructure
Build and maintain ETL/ELT pipelines and AI data workflows.
Orchestrate workflows using Airflow, Prefect, or Dagster.
Manage cloud data platforms such as Snowflake, BigQuery, or Redshift.
Deploy applications using Docker, Kubernetes, and CI/CD pipelines.
Performance & Reliability
Monitor application performance, inference latency, uptime, and model reliability.
Optimize AI systems for scalability, cost, and performance.
Implement secure authentication, permissions, and API protection.
Maintain compliance with industry security and privacy standards.
Collaboration
Partner with product managers, engineers, and data teams to deliver AI-powered features.
Translate prototypes into production-ready application
📌 Full-Stack AI Engineer (Perú)
🏢 Pavago
📍 Perú