AI Engineer

The Functionary; México; Presencial; MXN 1.200.000 - 1.800.000; Jornada completa

Descripción de la vacante

The Functionary in Mexico City is seeking a senior AI software engineer to build GenAI-powered experiences and a shared AI platform. You will own end-to-end features from conception to deployment, including RAG pipelines, personalization, and agentic workflows.

You will collaborate across teams to deliver production-grade AI, drive decisions, and contribute to a robust SDLC with strong testing and operational practices.

Formación

• Bachelor’s degree or equivalent professional experience.
• 7+ years of software development experience.
• 3+ years AI engineering experience.
• Python proficiency; production LLM experience.
• Specialization in RAG retrieval, LLM eval, or agent frameworks (LangChain/LlamaIndex).
• Prompts, context window management, and output quality tradeoffs familiarity.
• Vector databases, embeddings, or semantic search familiarity.
• AI-driven SDLC with AI-assisted tools (Claude Code, Copilot, Cursor).
• Familiarity with .NET/C#, Go, Python, Java, React, MS SQL Server, Azure or AWS.
• Full-stack awareness; ownership of features end-to-end.
• Code quality: testing, review, CI/CD.
• D3 (7+ yrs) and D4 (10+ yrs) progress toward broader contributions.

Responsabilidades

• Design, build, and operate production AI features: RAG pipelines, recommendations, conversational agents, or workflow automation.
• Build the shared AI platform layer: retrieval infra, eval frameworks, monitoring, guardrails, observability.
• Write LLM apps and integrations with marketing platforms, BI tools, or customer surfaces.
• Evaluate model and feature quality using structured eval frameworks; iterate prompts and retrieval strategies.
• Use AI-driven SDLC tooling daily for AI and non-AI code.
• Coordinate with the Personalization team to align features with ML signals.
• Document AI system design decisions and evaluation results in the knowledge base.

Conocimientos

Python

AI engineering

Full-stack awareness

Prompt engineering

RAG

LangChain

LlamaIndex

Evaluation frameworks

CI/CD

Cloud basics

Production ownership

Code quality

Educación

Bachelor's degree in Computer Science

Herramientas

Claude Code

GitHub Copilot

Cursor

LangChain

LlamaIndex

Descripción del empleo

Build the GenAI-powered product experiences and the shared AI platform infrastructure that powers them. This includes RAG pipelines over the client's catalog and customer reviews, LLM-driven personalization, a conversational Wellness Agent, agentic workflow systems, and the evals and MLOps layer that makes AI features production-grade and repeatable. Specializations within this track include: RAG and personalization, agent framework and tool use, evals and guardrails, and LLM application development for internal business functions such as marketing automation and BI agents.

Key Responsibilities:

• Design, build, and operate production AI features: RAG pipelines, LLM-driven recommendations, conversational agents, or agentic workflow automation.
• Build the shared AI platform layer: retrieval infrastructure, eval frameworks, model monitoring, guardrails, and observability.
• Write LLM applications and integrations with marketing platforms, BI tools, or customer-facing product surfaces.
• Evaluate model and feature quality using structured eval frameworks; iterate on prompts, retrieval strategies, and model selection using data.
• Use AI-driven SDLC tooling such as Claude Code as a daily practice for both AI and non-AI code.
• Coordinate with the Personalization team to align GenAI product features with existing ML personalization signals.
• Document AI system design decisions, evaluation results, and operational lessons in the shared knowledge base.

Requirements:

• Bachelor’s degree in Computer Science or equivalent professional experience
• 7+ years of professional software development experience
• 3+ years of professional AI engineering experience
• Python proficiency; comfortable building and operating production LLM applications.
• Hands-on experience with at least one specialization: RAG and retrieval systems, LLM evaluation, agentic frameworks (LangChain, LlamaIndex, or similar), or LLM-based workflow automation.
• Understanding of prompt engineering, context window management, and LLM output quality tradeoffs.
• Familiarity with vector databases, embedding models, or semantic search.
• AI-driven SDLC (required): hands‑on experience shipping production code with AI‑assisted development tools such as Claude Code, GitHub Copilot, or Cursor. The bar is not awareness; it is daily use in delivering real software.
• Familiarity with one or more: .NET/C#, Go, Python, Java, React, MS SQL Server, Azure or AWS.
• Full-stack awareness: comfortable contributing across layers of the stack when needed; purely single‑layer specialists are not the target profile.
• Production ownership: experience owning features end‑to‑end from spec through deployment and ongoing operations.
• Code quality fundamentals: strong grasp of software design principles, automated testing, code review, and CI/CD.
• D3 (7+ yrs): independently delivers features with some guidance; strong fundamentals; beginning to make broader technical contributions.
• D4 (10+ yrs): fully autonomous; drives technical decisions within the team; mentors junior engineers.

Nice to Haves:

• Experience with e-commerce platforms, product catalogs, or high‑traffic consumer applications.
• Exposure to MLOps tooling or model deployment pipelines.
• Experience working in distributed teams across the US, China, and Latin America.