Salsabil Maulana Akbar

AI & Machine Learning Engineer

Kuala Lumpur, Malaysia

AI professional with ~5 years of experience in Data Science & Machine Learning, applying a strong mathematics foundation to deliver end-to-end AI solutions across NLP, Speech, Computer Vision, and Tabular domains. Experienced in both startups and multinational corporations.

GitHub LinkedIn Hugging Face Google Scholar Semantic Scholar Email

🚀 Core Experience

Production Systems

Developed pricing models from scratch, improved search relevance, built fraud detection systems, and deployed scalable, long-lasting ML models into production.

Experiment Design & Impact Measurement

Designed experiments and A/B tests, and measured the quantitative impact of model changes on relevance, conversion, and key business metrics at scale.

Generative AI & Voice

Currently building and fine-tuning Speech & Text models with LLM-RAG integration, alongside pipelines for real-world voice AI applications.

Research

Published at EMNLP, ACL, and AACL on multilingual and low-resource NLP.

🛠️ Tech Stack & Where I Used It

Voice AI (current role): Python, LLMs & RAG, vLLM, Speech & audio models, FastAPI, AWS, Docker, Kubernetes, Airflow, DVC
Search & IR (Tokopedia, TikTok): Query understanding, retrieval & ranking, Vector Databases, model distillation & quantization, Airflow, GCP
Fraud & Risk (fintech startup): Graph Data Science (Neo4j), anomaly and network analysis, SQL, Airflow
Proptech (Pashouses): Multimodal modeling (tabular, text, image), ETL pipelines, GCP

🔭 Currently Exploring

Trustworthy AI

Actively growing into Explainable AI and Causal Inference, working toward AI that is trustworthy and interpretable.

📄 Selected Publications

Education & experience

Activities

Teaching & talks