Applied ML Engineer: Production‑Driven Modeling & Personalization

ActAI; Portugal; Presencial; EUR 65 000 - 95 000; Tempo integral

Resumo da oferta

ActAI is building AI-native mobile applications and ML-powered features. We seek an engineer to build and improve ML systems powering our AI-native apps, focusing on classification, retrieval, ranking, and personalization.

You will own model development to production deployment, develop evaluation pipelines, embeddings-based search, and personalization models while balancing latency, cost and privacy.

Qualificações

• Strong foundations in machine learning and modern neural architectures.
• Hands-on production experience with ML models.
• Experience in classification, ranking, retrieval or personalization.
• Understanding of evaluation, experimentation and performance metrics.
• Able to write production-quality code with real-world datasets.
• Balance model quality, latency, cost and reliability.

Responsabilidades

• Build and improve ML models for classification, ranking, retrieval and personalization.
• Develop efficient classifiers and optimize accuracy, latency and cost.
• Improve search relevance and context retrieval using embeddings, hybrid search and reranking.
• Build personalization models that learn from user behavior while respecting privacy.
• Develop evaluation pipelines, labeled datasets and metrics to measure model quality.
• Fine-tune and adapt existing models when supported by sufficient data.
• Build and maintain ML training, inference and deployment pipelines.
• Debug production issues, monitor model performance and ship improvements based on real-world feedback.

Conhecimentos

ML foundations

Production ML

Classification

Ranking

Retrieval

Personalization

Evaluation metrics

Code quality

Ferramentas

Python

PyTorch

JAX

Embeddings

Vector search

Descrição da oferta de emprego

ActAI is building AI-native mobile applications and ML-powered features. We seek an engineer to build and improve ML systems powering our AI-native apps, focusing on classification, retrieval, ranking, and personalization.

You will own model development to production deployment, develop evaluation pipelines, embeddings-based search, and personalization models while balancing latency, cost and privacy.