Job Description

What is this position about?

- Lead end-to-end project delivery with clear governance and strong stakeholder communication
- Mentor junior engineers and contribute to proposals and new business initiatives
- Define what AI systems should and should not attempt, and communicate risks and tradeoffs transparently to clients
- Design and build RAG systems, agentic frameworks, and LLM-powered solutions robust enough for production
- Apply advanced prompt engineering techniques, including instruction design, few-shot sets, structured outputs, and tool/agent prompts
- Lead feasibility assessments to select the right approach among prompting, RAG, fine-tuning, or classical ML
- Design evaluation frameworks, including LLM-as-a-judge methods, custom metrics (recall@k, precision@k),



and go/no-go gates
- Run structured experiments across prompts, retrievers, chunking strategies, and models, grounded in evidence rather than intuition
- Identify and categorize model failure modes, including hallucinations, retrieval misses, and instruction-following errors
- Build scalable inference infrastructure and CI/CD pipelines for AI/ML models
- Automate the full MLOps/LLMOps lifecycle, including tracking, versioning, deployment, monitoring, and retraining
- Design APIs, microservices, and orchestration layers optimized for latency, cost, and reliability

📌 AI Engineering Lead (Guadalajara)
🏢 Blend360
📍 Guadalajara