GenAI Application Engineer

Design, prototype, and deliver functional applications powered by artificial intelligence, prioritizing backend architecture and development.
The goal is to convert ideas into scalable and integrated solutions with generative AI — such as assistants, interactive dashboards, and reusable modules — using AI-assisted development tools and cloud services, maintaining high standards of quality, design, and performance.

Requirements

• Design and implement scalable and modular backend services, integrating generative AI components.
• Develop POCs and MVPs in short cycles, guaranteeing functionality and deployment in cloud environments.
• Apply Prompt Engineering for the effective orchestration of generative models.
• Integrate vector databases (Pinecone, OpenSearch, Chroma, Qdrant) and retrieval mechanisms (RAG).
• Implement fine-tuning and adaptation processes of AI models for specific cases.
• Create interactive dashboards and visualization environments (Amazon Quicksight or other tools).
• Collaborate with product, design, and data teams to integrate AI into visible system components.
• Document the architecture, technical decisions, and token economy of each solution.

• Education: Computer Engineering, Software Engineering, or related field.
• Experience: 3–5 years in software development, with emphasis on backend and scalable architectures.
• Level: Intermediate-advanced, with a genuine interest in applied AI and emerging tools.

• AI-assisted development tools: Cursor, Lovable, Kiro, Claude Code.
• Vector databases: Pinecone, OpenSearch, Chroma, Qdrant.
• Prompt Engineering (construction, evaluation, and versioning of prompts).
• Backend languages and frameworks: Node.js or Python (minimum 3 years of experience).
• Cloud & Deploy: AWS (Amplify, Lambda, Bedrock), Vercel, Supabase.

• Fine-tuning of AI models.
• Creation of interactive dashboards (Amazon Quicksight or equivalents).
• Frontend (functional level): React, Next.js or similar frameworks.
• REST / JSON API integration.

• Agent frameworks: LangGraph, CrewAI, Strands Agents.
• ETL processes: Pandas, Airbyte, DBT, Airflow, SQL, Snowflake or BigQuery.
• Model Context Protocol (MCP) and n8n for automation flows.
• Experience with RAG and design of generative AI pipelines.

• Ability to prototype quickly with a focus on backend and scalability.
• Mastery of the integration of generative models through APIs and cloud services.
• Systemic and results-oriented thinking.
• Ability to document and explain technical decisions clearly.
• Genuine interest in experimenting with new AI tools.

• Timely delivery of high-quality POCs and MVPs.
• Significant reduction of defects through AI-generated tests.
• Internal adoption of reusable GenAI modules by different teams.
• Accurate documentation on the use and token economy.
• Applications prepared for demonstrations, observability, and A/B testing.

Benefits

Integration into global brands and disruptive startups.

Remote work/Home office.

If a hybrid or in-person modality is required, you will be informed from the first session.

⏳ Schedule adjusted to the work cell/assigned project.

Work from Monday to Friday.

Day off on your birthday.

Major medical expense insurance (applies to Mexico).

️ Life insurance (applies to Mexico).

Multicultural work teams.

Access to courses and certifications.

Meetups with special guests from the IT area.

Virtual integration events and interest groups.

English classes.

Opportunities within our different business lines.

Proudly certified as a Great Place to Work.