Algorithm / Machine Learning Engineer (Junior to Senior)

COMMODITY INDEX SDN. BHD.; Kuala Lumpur; On-site; MYR 90,000 - 150,000; Full time

Job summary

COMMODITY INDEX SDN. BHD. in Kuala Lumpur seeks an Algorithm / Machine Learning Engineer (Junior to Senior) to transform business logic into ML-driven pricing models and to apply NLP on commodity market data.

You will design, develop, and maintain models with time-series forecasting and deep learning frameworks. The role requires strong Python/SQL, experience in ML/NLP, and the ability to translate complex analyst logic into robust engineering solutions.

Qualifications

• Bachelor’s degree or higher in CS/Math/Statistics/Data Science.
• Strong Python and SQL programming skills.
• Experience with ML, time-series forecasting, and DL frameworks.
• Experience in NLP including text classification and entity extraction.
• Ability to translate unstructured methodologies into engineering requirements.
• Nice to have commodity pricing or dynamic pricing experience.

Responsibilities

• Translate research methodologies into executable algorithmic pricing models.
• Design and maintain AI/ML–driven pricing and quotation models using time series.
• Apply NLP and data mining to commodity market data and reports.
• Develop algorithms with XGBoost, LightGBM, ARIMA, LSTM, PyTorch or TensorFlow.
• Build NLP solutions for classification, entity recognition, and summarization.
• Establish evaluation frameworks tracking daily quotation performance.
• Collaborate with BAs, Data Engineers and Product teams throughout lifecycle.

Skills

Python

SQL

Analytical thinking

Communication

Team collaboration

Education

Bachelor's degree in CS/Math/Statistics/Data Science

Tools

Pandas

NumPy

Scikit-learn

XGBoost

LightGBM

PyTorch

TensorFlow

ARIMA

LSTM

Job description

Algorithm / Machine Learning Engineer (Junior to Senior)

This role involves transforming business logic and research methodologies into executable algorithmic solutions. You will design, develop, and maintain AI/ML-driven pricing and quotation models, apply data mining and NLP techniques to commodity market data, and establish evaluation frameworks to optimize model performance based on market dynamics.

Key responsibilities

Understand and structure existing research methodologies, abstracting complex market insights and analyst logic into executable algorithmic solutions

Design, develop, and maintain AI/ML-driven pricing and quotation models using time-series forecasting and machine learning to ensure daily quote data is accurate and time-sensitive

Apply NLP and data mining techniques on commodity market data, analyst reports, and historical research to extract core pricing factors and market trends

Develop and optimize algorithms using XGBoost, LightGBM, ARIMA, LSTM, PyTorch, or TensorFlow

Construct NLP solutions for text classification, entity recognition, key information extraction, and automated summarization from unstructured research data

Establish evaluation frameworks to track daily quotation performance, continuously optimizing models based on market dynamics and analyst feedback

Work closely with Business Analysts, Data Engineers, and Product teams to drive the full lifecycle engineering implementation of pricing algorithms

About you

Bachelor's degree or above in Computer Science, Mathematics, Statistics, Financial Engineering, Data Science, or related fields

Strong programming skills in Python and SQL

Proficient with Pandas, NumPy, Scikit-learn, XGBoost, LightGBM, PyTorch, or TensorFlow

Hands-on experience in Machine Learning, time-series forecasting (e.g., ARIMA, LSTM), and Deep Learning frameworks

Proven practical experience in NLP, including text classification, entity extraction, and text summarization

Strong data sensitivity, logical thinking, and communication skills to break down unstructured methodologies into clear engineering requirements

Preferred: Experience in commodity pricing, quantitative finance, dynamic pricing, e-commerce pricing, or operations research optimization

Preferred: Knowledge of Knowledge Graphs, or hands-on experience in LLMs, AI Agents, and automated research report analysis

Preferred: Familiarity with big data processing frameworks (Spark, Hadoop, Flink) and MLOps (deploying and monitoring ML models in production)