Machine Learning Engineer

Company Description

Established in 2006, PT. INOSOFT TRANS SISTEM is a Surabaya-based software development company specializing in supply chain management solutions. We are committed not only to providing cutting-edge technology but also to fostering innovation, growth, and the professional development of our team.

Role Overview

We are looking for a full-time Machine Learning Engineer to join our team in Surabaya (hybrid) or fully remote. You will contribute to a strategic project to upgrade our internal supply chain platform into an intelligent, AI-driven system that provides automated, predictive KPI analytics for real-time decision-making.

This role requires a deep understanding of the machine learning lifecycle, from data labelling and augmentation to model deployment. You should be confident managing complex AI workflows involving synthetic data generation, data augmentation, deep learning model tuning, and integration into production software.

You will design and train predictive ML models to power KPI analytics, including but not limited to:

• Demand or lead time forecasting.
• Classification (e.g., predicting emergency order causes).
• Anomaly detection (e.g., unit cost spikes).
• Generating natural language explanations using LLM prompts.
  
  

Requirements

• Bachelor’s or Master’s degree in Computer Science, Data Science, or a related field.
• 3–5 years of hands-on experience building and deploying machine learning models.
• Strong Python skills, including Pandas, NumPy, and ML libraries such as Scikit-learn, XGBoost, or deep learning frameworks (e.g., TensorFlow, PyTorch).
• Experience with time-series modeling and training architectures such as LSTM, RNN, GRU, and 1D Neural Networks.
• Proficient in data wrangling and feature engineering, including data augmentation techniques (e.g., SMOTE).
• Familiarity with semi-structured or API-driven data sources, including JSON, MongoDB, or other NoSQL systems.
• Understanding of model evaluation metrics such as F1-score, RMSE, MAE, and experience applying K-Fold cross-validation.
• Experience working with large-scale datasets and automating AI workflows such as data tagging using GAN.
• Ability to build and deploy ML systems using Docker, FastAPI, or cloud platforms (e.g., GCP, AWS, SageMaker).
• Strong grasp of data preparation and feature engineering
• Excellent problem-solving abilities and a proactive learning attitude.
• Proficient in English (both written and verbal).
• Highly detail-oriented with strong time management skills.
• Strong communication skills and ability to collaborate across departments.
  
  

Job Description

• Managing and preprocessing large-scale, semi-structured datasets (e.g., JSON, MongoDB, external APIs).
• Generating labeled datasets using AI-assisted techniques such as GAN for KPI tagging.
• Applying data augmentation techniques (e.g., SMOTE) to improve model robustness on imbalanced datasets.
• Designing and training predictive models using 1D Neural Network, RNN, LSTM, GRU, including kernel and filter configuration.
• Building classification models to identify and explain causes of anomalies or order disruptions.
• Performing model validation using K-Fold cross-validation, with performance measured using metrics such as F1-score, RMSE, MAE.
• Deploying forecasting models to predict business KPIs from real-time data streams.
• Translating machine learning models into functional, modular software using tools like FastAPI, Docker, and GCP.
• Collaborating with cross-functional teams to integrate ML insights into dashboards and business workflows.
• Staying updated with advancements in LLMs, MLOps, and AI automation, and exploring how they can be applied in production.
  
  

Preferred / Nice To Have

• Experience using AWS SageMaker for model training, deployment, or pipeline automation.
• Experience building LLM-integrated systems (LangChain, HuggingFace, OpenAI, Amazon Bedrock).
• Previous experience with operational KPIs or business process modelling.
• Understanding of supply chain KPIs, manufacturing operations, or business forecasting.
• Experience with cloud platforms and scalable ML infrastructure (e.g., GCP, AWS, Kubernetes).
• Familiarity with CI/CD pipelines, model versioning, and MLOps tools (e.g., MLflow, Airflow).
  
  

APPLICATION PROCESS

Interested Candidates Should Submit Your Updated CV Along With

• Links to relevant Machine Learning projects or GitHub portfolio.
• A short note about your experience building ML models for business forecasting or classification.
• A 100-word proposal on how you would forecast supplier lead times using Machine Learning.
• You may write your responses in English or Bahasa Indonesia.
  
  

Be part of a team that transforms raw data into real-world insights through smart, AI-powered systems. Let’s shape the future of intelligent supply chains together.