AI Engineer

Keyrus; Nezahualcóyotl; Remote; MXN 700,000 - 1,200,000; Full time

Benefits offered by this job

International projects

Continuous learning and professional发展

Career growth and internal mobility

Job summary

Keyrus seeks a Senior AI Engineer to design, build, evaluate, and deploy intelligent GenAI systems that integrate into business processes. You will own AI behavior, reliability, and performance while collaborating with software, data, and governance teams.

You will work on RAG architectures, AI agents, tool use, and enterprise integrations, ensuring scalable, production-ready solutions with measurable business value.

Qualifications

• Hands-on experience designing, developing, and deploying GenAI and LLM-based solutions.
• Proven experience with RAG architectures, AI agents, and multi-step workflows.
• Experience evaluating, monitoring, and optimizing AI systems for reliability, performance, and cost.
• Strong software engineering background, including API development, testing, and enterprise integrations.

Responsibilities

• Design and deploy production-ready GenAI solutions, including RAG systems and intelligent assistants.
• Engineer AI agent behavior, including tool use, context management, memory, routing, failure handling, and human oversight.
• Integrate LLMs, APIs, enterprise applications, and data sources while balancing performance, latency, and cost.
• Build evaluation frameworks, automated tests, and quality controls to measure AI reliability and detect regressions.

Skills

GenAI design

RAG architectures

AI agents

API development

Python

LLM integration

Cloud platforms

Tools

LangChain

LangGraph

LlamaIndex

Semantic Kernel

Azure/AWS/GCP

Job description

Why Keyrus, Why Now!

Keyrus is an international group of 3,000 experts across 30 countries, built on a single conviction: AI does not transform businesses. Architected intelligence does.

For over 30 years, we have helped organizations build the data foundations that power intelligent systems. Today, we go further — designing and operationalizing intelligence that delivers measurable business value.

At Keyrus, you'll develop the engineering judgment to turn AI models into reliable, production-ready capabilities that integrate into real business processes.

Technology amplifies. Keyrus culture differentiates.

What you’ll architect

As an AI Engineer, you’ll design, build, evaluate, and deploy intelligent systems combining Large Language Models, retrieval architectures, AI agents, and enterprise integrations.

You’ll own AI behavior, quality, and reliability while collaborating with Software Engineers, Data Engineers, Architects, and Governance specialists.

Your responsibilities

• Design and deploy production-ready GenAI solutions, including RAG systems, intelligent assistants, and agentic workflows.
• Engineer AI agent behavior, including tool use, context management, memory, routing, failure handling, and human oversight.
• Integrate LLMs, APIs, enterprise applications, and data sources while balancing performance, latency, and cost.
• Build evaluation frameworks, automated tests, and quality controls to measure AI reliability and detect regressions.
• Monitor, troubleshoot, and continuously improve AI capabilities in production.
• Document reusable engineering patterns and enable client teams to maintain and extend deployed solutions.

Who you are

You’re a hands‑on engineer who understands that successful AI goes beyond model performance. You combine strong software engineering fundamentals with practical problem‑solving, technical judgment, and a focus on reliable, measurable business outcomes.

What you bring

Experience

• Hands‑on experience designing, developing, and deploying production‑ready GenAI and LLM‑based solutions.
• Proven experience with RAG architectures, AI agents, and multi‑step intelligent workflows.
• Experience evaluating, monitoring, and optimizing AI systems for reliability, performance, and cost.
• Strong software engineering background, including API development, testing, and enterprise integrations.

Technical skills

• Strong Python programming and software development fundamentals.
• LLM integration, prompt engineering, embeddings, retrieval, and grounding techniques.
• AI agent orchestration, tool calling, context management, memory, and human‑in‑the‑loop workflows.
• LLM evaluation, automated testing, observability, and production monitoring.
• Familiarity with cloud platforms (Azure, AWS, or GCP), CI/CD, and LLMOps/MLOps practices.

Nice to have

• Experience with LangGraph, LangChain, LlamaIndex, or Semantic Kernel.
• Knowledge of multi‑agent systems, multimodal AI, fine‑tuning, or open‑source models.
• Experience integrating AI with CRM, ERP, MCP, or enterprise automation platforms.
• Consulting experience or exposure to regulated industries.

Technology examples are illustrative; expertise in every platform is not required.

Role details

• Location: Mexico & Colombia
• Seniority: Senior
• Work model: Remote

Rewards – What we offer at Keyrus

• International and multicultural projects.
• Continuous learning and professional development.
• Career growth and internal mobility opportunities.
• A collaborative, innovative, and entrepreneurial culture.

Local benefits and working arrangements will be confirmed before publication.

About Keyrus

At Keyrus, we help organizations move from experimental AI to industrialized AI, from isolated agents to orchestrated systems, and from insight to execution.

Powered by our proprietary Human Orchestrated Model™ (HOM), we build intelligent environments around three pillars: Intelligence Foundations, Human in Command, and Performance Steering.

With 30+ years of expertise across 30 countries, we design intelligent systems that amplify human capabilities and create sustainable business value.

AI does not transform businesses. Architected intelligence does.

Learn more: www.keyrus.com