Senior Generative AI Engineer — Production LLMs

Blend360; Región Centro; Hybrid; MXN 900,000 - 1,600,000; Full time

Benefits offered by this job

AWS Certification

Databricks

Snowflake

Udemy Business

English lessons

Travel opportunities

Mentoring and Development

Flexible working options

Company-provided equipment

Job summary

Blend is seeking a Senior AI Engineer to design, architect, and deploy advanced Generative AI solutions in production, focusing on LLM-based systems, agentic workflows, and cross-functional collaboration with Engineering, Product, and MLOps teams.

The ideal candidate combines hands-on technical depth with solid software engineering practices and will guide AI projects from design through production, balancing scalability and business impact.

Qualifications

• Degree in Computer Science, Data Science, Engineering, or related field (or equivalent practical experience).
• Strong expertise in transformer-based models and LLM architectures.
• Proven experience designing and deploying applied machine learning or generative AI systems to production environments.
• Hands-on experience with LLM frameworks such as LangChain, LlamaIndex, OpenAI API, CrewAI, Azure Prompt Flow, AWS Bedrock Agents, or similar tools.
• Advanced proficiency in Python and production-grade coding practices.
• Experience with containerization, CI/CD pipelines, versioning, and cloud-native architectures.
• Strong leadership skills with the ability to bridge rapid prototyping and scalable production deployment.
• Excellent collaboration and communication skills, with experience working at the intersection of Data Science and Engineering.

Responsibilities

• Contribute to the architecture and implementation of production-grade AI solutions leveraging LLMs, transformer-based models, RAG pipelines, and agentic systems.
• Design, develop, and optimize multi-step AI agents capable of tool/API invocation, reasoning chains, and state management.
• Support the deployment and optimization of AI-powered applications across cloud environments (AWS, Azure, or GCP), ensuring scalability, reliability, and cost-efficiency.
• Contribute to best practices for prompt engineering, evaluation frameworks, and model performance monitoring (latency, grounding, factuality, cost).
• Implement guardrails and Responsible AI practices, including prompt injection mitigation, content moderation, bias reduction, and safety controls.
• Collaborate cross-functionally with Data Scientists, Software Engineers, and Product stakeholders to take AI solutions from prototype to full production.
• Share knowledge and support other engineers in developing high-quality, modular, and maintainable Python code.
• Contribute to experimentation strategies, help define KPIs, and promote data-driven decision-making across AI initiatives.

Skills

LLM architectures

Transformer models

Python

CI/CD

Containerization

Leadership

Cross-functional collaboration

Education

Bachelor's degree in CS/DS/Engineering

Tools

LangChain

LlamaIndex

OpenAI API

Azure Prompt Flow

AWS Bedrock Agents

Job description

Blend is seeking a Senior AI Engineer to design, architect, and deploy advanced Generative AI solutions in production, focusing on LLM-based systems, agentic workflows, and cross-functional collaboration with Engineering, Product, and MLOps teams.

The ideal candidate combines hands-on technical depth with solid software engineering practices and will guide AI projects from design through production, balancing scalability and business impact.