Senior Python & Agentic AI Engineer (Remote – Colombia/Costa Rica)

About the role

Gorilla Logic is seeking a Senior Python & Agentic AI Engineer to design and deliver production‑grade AI features for a cybersecurity and GRC assessment platform. The role is fully remote and open to candidates residing in Colombia or Costa Rica.

Key responsibilities

• Design and implement AI‑agent features that generate customer‑specific recommendations, tasks, and findings.
• Build production‑ready Python services using modern asynchronous patterns.
• Develop secure, high‑performance APIs with FastAPI or equivalent frameworks.
• Create agent workflows with Pydantic AI, LangGraph, or similar tools, including tool‑calling and structured outputs.
• Integrate LLM APIs from providers such as Anthropic and OpenAI.
• Design, test, and maintain prompts for production AI applications.
• Construct retrieval‑augmented generation pipelines using embeddings, chunking, and vector search.
• Implement safeguards to improve AI output accuracy, consistency, and safety.
• Handle confidential customer data responsibly and ensure compliance with privacy standards.
• Build persistence layers with SQL and SQLAlchemy, and write unit/integration tests using pytest.
• Collaborate in pull‑request reviews, CI workflows, and Docker‑based development environments.
• Monitor and optimise AI‑service cost, latency, reliability, and performance.

Required profile

• Bachelor’s degree in Computer Science, AI, Data Science, or related field, or equivalent professional experience.
• 5+ years of professional Python development experience.
• Strong background in asynchronous Python and production API development.
• Proven experience delivering production LLM‑powered applications and agentic workflows.

Required skills

• Python (asyncio, modern syntax)
• FastAPI or comparable async web framework
• Pydantic AI, LangGraph or similar agent frameworks
• Prompt engineering for LLMs
• Integration with Anthropic, OpenAI or comparable LLM APIs
• SQL, SQLAlchemy ORM
• pytest for testing
• Docker for containerised development