AI/ML Engineer (Hybrid NLP + Classification)

TL;DR

AI/ML Engineer (Hybrid NLP + Classification): design and build hybrid rule-based plus ML system mapping contractor free-text to 4-tier SAP catalog hierarchy, flagging anomalies, and implementing feedback loop for model retraining from operator corrections. Focus on building classification pipeline, anomaly detection module, and wrapping model as microservice for integration.

Location: 100% remote for candidates based in LATAM, Eastern Time overlap for gate and sprint reviews.

Company

hirify.global curates top Latin American tech talent for global clients, including a Fortune 500 energy company migrating Plant Maintenance data to SAP S/4HANA.

What you will do

• Author the AI/ML architecture design document readable by non-technical stakeholders.
• Recommend accuracy threshold and build 4-tier catalog code mapping engine for SAP types.
• Implement AI anomaly detection module for tabular data.
• Design and implement feedback loop where operator corrections retrain the model.
• Wrap the model as a microservice for the main web application.

Requirements

• Candidates must be based in LATAM.
• NLP and text classification in Python using scikit-learn or HuggingFace transformers.
• Rule-based NLP with keyword extraction, regex, and scoring logic.
• ML classification pipeline including data preparation, evaluation, and tuning.
• Anomaly detection in tabular data.
• Python data science stack: pandas, numpy, scikit-learn, optionally spaCy.
• Model feedback loop design and API/microservice wrapping of ML models.

Nice to have

• Precision/recall trade-off framing for catalog mapping.
• SAP catalog code domain knowledge.

Culture & Benefits

• 100% remote work with BYOD.
• Payment in USD.
• People-centered culture promoting innovation, collaboration, and professional development.
• Small senior team in 8 Agile-Scrum sprints over 16 weeks, 6-10 hours/week active (60 hours total).