AI Engineer (Agentic Systems / LLMs)

Role overview

Build and deploy AI agents for conversational and business workflows, connecting language models to the services and data they need to complete useful tasks. The work spans system design, implementation, integration, and ongoing evaluation, with attention to agent reliability, response quality, speed, and operating cost.

Responsibilities - Develop, test, and deploy stateful, scalable agents in Python using suitable frameworks and model APIs. - Integrate agents with data sources, internal services, and external APIs to support end-to-end workflows. - Create evaluation and monitoring pipelines to measure agent behavior and guide improvements. - Refine prompts, retrieval-augmented generation, and tool connections for accuracy and efficiency. - Keep current with generative AI techniques and apply them to practical product needs.

Requirements - Senior-level experience building LLM-powered applications and agent architectures. - Strong Python engineering skills and experience deploying production software. - Practical knowledge of agent frameworks and model APIs, such as LangChain, LlamaIndex, CrewAI, Google ADK, or the OpenAI SDK. - Experience integrating AI systems with APIs, services, and data sources. - Advanced English (C1) and ability to coordinate with distributed teams across US and LATAM time zones. - Full-time availability for the role; other professional activities must be disclosed and must not conflict with work hours or responsibilities.

Benefits and work setup

Remote contractor engagement, with coordination across US, LATAM, and global teams. The project focuses on fintech, conversational AI, and agentic workflows.