Senior Python & Agentic AI Engineer - GP, Remote: Colombia - Costa Rica, Fulltime.

Gorilla Logic is looking for a Senior Python and Agentic AI Engineer, who will work with a team of developers, AI engineers, and product stakeholders building production-grade artificial intelligence features for a cybersecurity and GRC assessment platform. This role will be responsible for developing Python-based AI services that generate customer-specific recommendations, tasks, and findings. These capabilities will be exposed through APIs and consumed by a .NET application. Our environment will require you to combine advanced Python engineering with production LLM development, agentic workflows, retrieval-augmented generation, evaluation, security, and responsible handling of sensitive data. Responsibilities Design and build AI-agent features that generate tailored customer recommendations, tasks, and findings Develop production Python services using modern asynchronous Python Build secure APIs using FastAPI or a comparable asynchronous Python web framework Develop agent workflows using Pydantic AI, LangGraph, or similar frameworks Implement tool-calling, structured outputs, and multi-step agent workflows Integrate large language model APIs from providers such as Anthropic and OpenAI Design, test, and maintain prompts for production AI applications Build retrieval-augmented generation pipelines using embeddings, chunking, and vector search Design data-ingestion, indexing, retrieval, and context-building workflows Develop safeguards to improve AI output accuracy, consistency, and safety Evaluate hallucination, accuracy, grounding, and other output-quality risks Handle confidential customer information and personally identifiable information responsibly Build persistence layers using SQL and an ORM such as SQLAlchemy Write unit and integration tests using pytest Develop services that can be securely consumed by the .NET application and other internal systems Participate in pull-request reviews and continuous integration workflows Monitor and optimize AI-service cost, latency, reliability, and performance Work closely with internal AI, platform, product, and application engineering teams Develop and test services within a Docker-based environment Communicate AI behavior, limitations, risks, and technical trade-offs clearly Technical Requirements Bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field, or equivalent professional experience 5+ years of professional Python development experience Strong experience with modern asynchronous Python Experience building APIs with FastAPI or a comparable asynchronous Python framework Proven experience building and operating production LLM-powered applications Experience with agent frameworks such as Pydantic AI, LangGraph, or similar technologies Experience implementing tool-calling and structured model outputs Strong prompt-engineering experience Experience integrating Anthropic, OpenAI, or comparable LLM APIs Experience building retrieval-augmented generation solutions Strong understanding of embeddings, chunking, retrieval, and vector search Experience evaluating AI outputs for accuracy, hallucination, and safety Experience implementing AI guardrails and validation mechanisms Strong understanding of secure and responsible handling of sensitive data and PII Experience with SQL and an ORM such as SQLAlchemy Experience writing automated tests using pytest Experience with Git pull-request workflows and continuous integration Experience with Docker and GitHub Actions or comparable CI technologies Strong written communication and asynchronous collaboration skills Ability to maintain reasonable daily working-hours overlap with a US-based technical lead Ability to independently design and deliver complex AI capabilities Comfortable using AI-assisted development tools Must have the ability to work in a dynamic and highly collaborative environment Strong analytical thinking and problem-solving skills Bonus Skills Experience with LLM gateways or proxy tools such as LiteLLM Experience with PII detection or anonymization tools such as Microsoft Presidio Experience with PostgreSQL and pgvector Experience with asynchronous SQLAlchemy Experience with Alembic Experience with LLM observability, tracing, and evaluation frameworks Experience optimizing AI systems for cost, latency, and throughput Experience designing APIs consumed by multiple applications Experience with conversational user-interface tools such as Chainlit Experience in cybersecurity, GRC, fintech, or financial services