AI Engineer (GenAI / LLM) - LATAM
Posted
Summary
Builds and ships production-grade generative AI: LLM applications, RAG pipelines, and autonomous agents using LangChain/LangGraph, vector databases, and multi-provider LLMs (OpenAI, Anthropic, Gemini), deployed and monitored on AWS/GCP/Azure. Needs 4+ years of Python and real production LLM experience; remote role for LATAM candidates.
Descripción del puesto
We're looking for an AI Engineer to build and ship production-grade generative AI solutions: intelligent assistants, RAG systems, and autonomous agents. 100% hands-on role with end-to-end ownership: architecture, deployment, monitoring, and continuous improvement. Not research, not POCs — making it work in production.
💼 What you'll do
- Build LLM applications and AI agents with LangChain / LangGraph or similar.
- Implement RAG pipelines: embeddings, vector databases, hybrid search.
- Integrate multiple LLMs (OpenAI, Anthropic, Gemini, open source) based on cost, latency, and quality.
- Deploy on cloud (AWS / GCP / Azure) and monitor performance, drift, and cost.
- Implement LLM evals to ensure response quality.
Requisitos
✅ What we're looking for
- 4+ years developing with Python.
- Real production experience with LLMs: prompt engineering, RAG, tool calling.
- Hands-on with vector databases (Pinecone, Chroma, pgvector).
- Cloud + solid engineering practices: testing, version control, CI/CD.
- Intermediate/advanced English.
⭐ Nice to have
- Agent frameworks (CrewAI, AutoGen) and protocols like MCP.
- Fine-tuning of open-source models, MLOps.
- Experience with US / European clients.