Production ML Engineer - Personalization & Retrieval

GMP RECRUITMENT SERVICES (S) PTE LTD; Singapore; On-site; SGD 80,000 - 120,000; Full time

Job summary

GMP Technologies (S) Pte Ltd is seeking an ML Engineer to develop and deploy production ML models, focusing on classification, ranking, retrieval and personalisation. You will build robust pipelines and work on embeddings, vector search, and hybrid retrieval to improve relevance while balancing latency and cost.

The role requires hands-on experience with ML systems in production, strong coding skills in Python, and a solid foundation in neural networks.

Qualifications

• Hands-on experience building and deploying ML models in production.
• Strong sense of ownership and problem-solving ability.
• Comfortable writing production-quality code and working with real-world datasets.
• Experience in classification, ranking, retrieval, recommendation systems or personalisation.
• Solid grounding in machine learning and modern neural network architectures.

Responsibilities

• Investigate production issues, track model performance and roll out improvements based on real-world feedback.
• Create and refine ML models for classification, ranking, retrieval and personalisation.
• Set up evaluation pipelines, labelled datasets and metrics to measure model quality.
• Enhance search relevance and context retrieval using embeddings, hybrid search and re-ranking.
• Build and maintain pipelines for ML training, inference and deployment.
• Develop efficient classifiers and optimise for accuracy, precision, latency and cost.
• Fine‑tune and adapt existing models where sufficient data is available.
• Design personalisation models that learn from user behaviour while respecting user privacy.

Skills

Model evaluation

Production ML

Python

Embeddings

Vector search

Ranking models

PyTorch

JAX

Performance tuning

Tools

PyTorch

JAX

Vector search

Job description

GMP Technologies (S) Pte Ltd is seeking an ML Engineer to develop and deploy production ML models, focusing on classification, ranking, retrieval and personalisation. You will build robust pipelines and work on embeddings, vector search, and hybrid retrieval to improve relevance while balancing latency and cost.

The role requires hands-on experience with ML systems in production, strong coding skills in Python, and a solid foundation in neural networks.