22 days ago
Mexico City, MexicoStaff+
Responsibilities
- Design and build architectures for AI agents and copilots covering tool use, orchestration, retrieval, memory, and multi-step reasoning.
- Take agentic systems into production and own deployment, observability, latency, cost, error handling, and graceful degradation.
- Build and maintain evaluation pipelines, guardrails, and monitoring to detect regressions and quality drift.
- Own production reliability through on-call readiness, incident response, and root-cause fixes.
- Drive cross-functional engineering initiatives from scoping and stakeholder alignment through production delivery.
- Define and promote engineering standards, patterns, and best practices for agentic and generative AI systems.
- Make architecture, framework, model-provider, retrieval, and orchestration trade-off decisions.
- Mentor engineers and raise the technical bar for agent engineering across the organization.
Requirements
- Extensive software engineering experience and a track record of leading complex, high-impact initiatives at IC5/Staff level.
- Evidence of shipping and operating an AI agent, copilot, or agentic system serving real users and production traffic.
- Strong software engineering foundation with hands-on ownership of production code.
- Ability to reason about agents as distributed systems with failure modes and make latency, quality, autonomy, control, cost, and accuracy trade-offs.
- Ability to lead autonomous cross-functional initiatives with Product, Design, Data Science, research, and business stakeholders.
- Experience working in collaborative, multidisciplinary environments.
- Hands-on experience with agent frameworks or orchestrators such as LangGraph or LangChain is preferred.
- Experience with LLM provider APIs such as Claude, OpenAI, or Gemini, vector databases, and evaluation frameworks is preferred.
- Experience designing evaluation and guardrail systems for LLM-based products is preferred.
- Experience with financial products, operations, support, growth, loyalty, or digital ecosystems is preferred.
- Interest in agent design, human-in-the-loop systems, AI trust, explainability, and responsible AI is preferred.
Categories
