
Applied AI Engineer – LLMs & Agentic Systems
Posted 6 days ago

Posted 6 days ago
This is a fully remote position, open to applicants in Mexico, +4 more countries.
• Design, develop, and maintain applications based on LLMs utilized in real business processes.
• Build agent-based systems capable of interacting with tools, APIs, and external services while incorporating controls over their actions.
• Assess when it is advantageous to use agents, deterministic workflows, or a combination of both.
• Design and implement RAG solutions, including strategies for chunking, embeddings, retrieval, reranking, and context management.
• Implement evaluation mechanisms to measure the quality of responses, information retrieval, and agent behavior.
• Identify and resolve issues related to hallucinations, execution errors, latency, costs, and reliability.
• Define validation mechanisms, error handling, and monitoring for solutions deployed in production.
• Collaborate with product and engineering teams to understand business requirements, evaluate alternatives, and translate them into viable technical solutions.
• Participate directly in architecture, implementation, and continuous improvement decisions for the developed solutions.
• Practical experience in building and operating LLM-based applications in production, beyond prototypes or proof of concepts.
• Direct participation in architecture and implementation decisions for solutions with agents.
• Experience implementing tool calling and integrations with external APIs or services.
• Hands-on knowledge of context management, state, and memory in applications using LLMs.
• Ability to justify when to use an agent versus resolving a problem through deterministic logic.
• Experience implementing RAG pipelines for real applications.
• Knowledge of chunking strategies, embeddings, semantic search, and document retrieval.
• Experience in evaluating and enhancing the relevance of retrieved information.
• Ability to identify retrieval issues and minimize incorrect or unsupported responses.
• Experience in implementing quality assessments for LLM applications, including tests on responses and agent behavior.
• Practical knowledge of mechanisms for detecting and mitigating hallucinations, errors, and inconsistent responses.
• Experience identifying latency issues, token consumption, and inference costs.
• Ability to diagnose failures and enhance the reliability of solutions in production.
• Solid experience in developing solutions with Python.
• Experience integrating APIs, backend services, and language models.
• Adherence to best practices in development, testing, error handling, and application maintenance.
• Autonomy in investigating problems, proposing alternatives, and executing end-to-end solutions.
• Desirable: experience with agent orchestration frameworks such as LangGraph, Pydantic AI, or similar.
• Desirable: experience implementing integrations using Model Context Protocol (MCP).
• Desirable: knowledge of vector databases and semantic search tools.
• Desirable: experience with observability tools and LLM application evaluation.
• Desirable: knowledge of Machine Learning and Data Science.
• Desirable: experience in fintech, financial services, payments, fraud, or regulated processes.
• Desirable: familiarity with security controls and protection of sensitive information in AI applications.
• Integration with global brands and disruptive startups.
• Remote work/Home office.
• Flexible hours according to the assigned work/project team.
• Work from Monday to Friday.
• Day off on your birthday.
• Major medical expense insurance (applies to Mexico).
• Life insurance (applies to Mexico).
• Access to courses and certifications.
• English classes.
• Opportunities within our various business lines.
Extend
OhioHealth
Capital One
Software Mind
Get handpicked remote jobs straight to your inbox weekly.