Job Description

As part of this role, you will be responsible for:

- Leading AI project delivery end to end, ensuring clear governance, strong stakeholder communication, and reliable execution.
- Designing and building robust RAG systems, agentic frameworks, and LLM-powered solutions suitable for production environments.
- Applying advanced prompt engineering techniques, including instruction design, few-shot prompting, structured outputs, and tool/agent prompts.
- Leading feasibility assessments to determine the right technical approach, including prompting, RAG, fine-tuning, classical ML, or hybrid solutions.
- Designing evaluation frameworks for AI systems, including LLM-as-a-judge, custom metrics, recall@k, precision@k, and go/no-go gates.
- Running structured experiments across prompts, retrievers, chunking strategies, embeddings,



reranking approaches, and models.
- Identifying and categorizing model failures such as hallucinations, retrieval misses, instruction-following errors, and quality regressions.
- Building scalable inference infrastructure and CI/CD pipelines for AI and ML models.
- Automating the MLOps/LLMOps lifecycle, including tracking, versioning, deployment, monitoring, retraining, and continuous improvement.
- Designing APIs, microservices, and orchestration layers optimized for latency, cost, reliability, and scalability.
- Mentoring junior engineers and contributing to proposals, solution design, and new business initiatives.

📌 AI Engineer Manager (Guadalajara)
🏢 Blend360
📍 Guadalajara