AI Engineer

We're looking for an AI Engineer who wants to take LLM, RAG and agent solutions from prototype to production. You'll design and implement applied AI products for the company, working 100% remotely from LATAM.

• 5+ years as a software or ML engineer, with 2+ years building products with LLMs.

• English B2 or higher (mandatory).

• Daily use of AI tools to code and boost productivity (GitHub Copilot, Cursor, Claude Code or similar).

• Advanced Python and APIs with FastAPI.

• Experience with LangChain, LlamaIndex or equivalent frameworks.

• Vector databases (Pinecone, Weaviate, pgvector, Qdrant).

• Prompt engineering and output evaluation techniques.

• Docker and deployment on AWS, GCP or Azure.
  Responsibilities

• Build applications on top of LLMs (OpenAI, Anthropic, open source models).

• Design the architecture of RAG pipelines: ingestion, chunking, embeddings and vector databases.

• Develop agents and tool-based workflows (tool calling, orchestration).

• Define evaluation strategies for model quality, cost and latency.

• Deploy and monitor AI services in production.

Nice to have

• Model fine-tuning and Hugging Face.

• MLOps (MLflow, Weights & Biases) and LLM observability (LangSmith, Langfuse).

• Background in traditional machine learning (scikit-learn, PyTorch).

• Multimodal models (vision, voice) and Model Context Protocol (MCP).

• Personal projects, demos or open source contributions in AI.

• 100% remote from any country in Latin America, no relocation needed.

• Flexible hours with partial overlap with the client's time zone.

• Applied AI projects in production: LLMs, RAG and agents.

• Constant exposure to cutting-edge tools and models.