What you’ll work onDesign and build production-ready LLM applications and AI agents.Develop RAG systems using private and structured company data.Create backend services and APIs with Python and FastAPI.Build document ingestion, chunking, embedding and retrieval pipelines.Evaluate answer quality, retrieval performance, latency and cost.Implement monitoring, guardrails, access controls and fallback mechanisms.Integrate AI capabilities with existing products and business workflows.Collaborate with data engineers, software developers and product stakeholders.Make technical decisions around architecture, scalability and reliability.Mentor other engineers and contribute to engineering standards.What we’re looking forStrong professional experience with Python and backend engineering.Hands-on experience building and deploying generative AI applications.Practical knowledge of LLMs, RAG, embeddings and vector databases.Experience with frameworks such as LangChain, LangGraph, LlamaIndex or similar.Experience designing APIs,



asynchronous workflows and distributed systems.Familiarity with cloud platforms such as AWS, Azure or GCP.Understanding of data pipelines, SQL and data integration.Experience with Docker, CI/CD, testing and production monitoring.Ability to evaluate AI output beyond “it looks good.”Clear communication and the confidence to challenge weak technical assumptions.Nice to haveExperience with agentic workflows and tool-calling systems.Knowledge of MLOps, LLMOps or model evaluation frameworks.Experience with OpenAI, Anthropic, Gemini or open-source models.Familiarity with PostgreSQL, pgvector, Pinecone, Weaviate, Qdrant or similar.Experience with streaming, event-driven systems or workflow orchestration.Previous experience working in a consultancy, startup or product studio.What matters to usWe value engineers who are curious, practical and honest about what AI can—and cannot—do.You should care about building systems that are:#J-18808-Ljbffr

📌 Ai Engineer (Colombia)
🏢 Latzu Digital Labs
📍 Colombia