Machine Learning Engineer

ChemLex; Singapore; On-site; SGD 90,000 - 120,000; Full time

Job summary

ChemLex in Singapore is seeking a Machine Learning Engineer to work at the intersection of artificial intelligence, data science, chemistry and scientific computing. You will handle statistical modelling, ML, data engineering, image analysis, automation and LLM-based approaches depending on the problem at hand.

The role is hands‑on and broad, requiring programming, problem solving and a willingness to learn new methods to solve real‑world R&D challenges.

Qualifications

• Bachelor's or Master's degree in Data Science, Computer Science, Engineering, Chemical Engineering, Chemistry or a related quantitative or scientific discipline.
• At least 2 years of relevant working experience in AI, data science, scientific computing, machine learning, software development or a related technical field.
• Good proficiency in Python for data processing, modelling, scientific computing and automation.
• Experience with scientific and data-processing libraries such as pandas, NumPy and RDKit or equivalent tools.
• Good understanding of statistical analysis and supervised and unsupervised machine-learning methods.
• Familiarity with databases, SQL, APIs and structured or semi-structured data.
• Familiarity with LLMs and their practical application to information extraction, analysis or automation.
• Understanding of structured software development, version control and reusable code.
• Ability to work effectively with complex, imperfect and heterogeneous real-world data.
• Strong analytical, problem-solving and communication skills.
• Background in chemistry, chemical engineering, scientific computing or computational science.
• Familiarity with chemical reactions, crystallisation and liquid‑liquid extraction.
• Experience working with experimental, analytical or high‑throughput datasets.
• Experience with statistical modelling, time‑series analysis, neural networks or deep learning.
• Experience with computer vision, image processing or multimodal models.
• Experience building data pipelines, APIs, internal tools or automated computational workflows.
• Experience extracting structured information from scientific literature or technical documents.
• Experience with LLM tool calling, RAG, AI agents or agentic workflows.
• Experience with laboratory automation, scientific instruments or sensor‑generated data.
• Familiarity with cheminformatics or chemical data.

Responsibilities

• Work with scientists and engineers to understand scientific problems and translate them into practical AI, data, modelling and computational solutions.
• Explore, analyse and interpret complex scientific and experimental data using appropriate statistical, computational and machine-learning methods.
• Develop statistical and machine-learning models, including regression,classification, clustering, time-series modelling, anomaly detection and neural networks.
• Develop reliable data pipelines and automated workflows for processing, validating and integrating data from different sources and systems.
• Develop image-analysis and computer-vision workflows for scientific and experimental applications.
• Develop LLM and AI-assisted workflows for information extraction, scientific literature processing, knowledge organisation and automation.
• Build Python tools, visualisations and reusable computational workflows to support scientific research and decision-making.
• Explore, evaluate and adopt emerging AI and computational technologies where they can improve scientific workflows, analysis and automation.

Skills

Python

Pandas

NumPy

RDKit

Statistical analysis

Supervised learning

Unsupervised learning

LLM tool calling

Data pipelines

Computer vision

Multimodal models

APIs

Git / Version control

Education

Bachelor's or Master's in Data Science/CS/Engineering/Chemical Engineering/Chemistry

Tools

RDKit

SQL

APIs

Git

Job description

We are looking for Machine Learning Engineer to work at the intersection of artificial intelligence, data science, chemistry, scientific computing and laboratory automation.

You will work across a variety of scientific and technical projects, applying statistical modelling, machine learning, neural networks, data engineering, image analysis, automation and LLM-based approaches depending on the problem at hand.

The role is intentionally broad and flexible. You may work with structured experimental data, images, sensor and time-series data, scientific literature, laboratory systems or other scientific information sources, and develop appropriate computational solutions for each problem. This is a hands‑on technical role suited for someone who enjoys programming, scientific problemsolving, investigating unfamiliar problems and learning new methods to solve real‑world R&D challenges.

Key responsibilities

• Work with scientists and engineers to understand scientific problems and translate them into practical AI, data, modelling and computational solutions.
• Explore, analyse and interpret complex scientific and experimental data using appropriate statistical, computational and machine-learning methods.
• Develop statistical and machine-learning models, including regression,classification, clustering, time-series modelling, anomaly detection and neural networks.
• Develop reliable data pipelines and automated workflows for processing, validating and integrating data from different sources and systems.
• Develop image-analysis and computer-vision workflows for scientific and experimental applications.
• Develop LLM and AI-assisted workflows for information extraction, scientific literature processing, knowledge organisation and automation.
• Build Python tools, visualisations and reusable computational workflows to support scientific research and decision-making.
• Explore, evaluate and adopt emerging AI and computational technologies where they can improve scientific workflows, analysis and automation.

Necessary qualifications and qualities

• Bachelor's or Master's degree in Data Science, Computer Science, Engineering, Chemical Engineering, Chemistry or a related quantitative or scientific discipline.
• At least 2 years of relevant working experience in AI, data science, scientific computing, machine learning, software development or a related technical field.
• Good proficiency in Python for data processing, modelling, scientific computing and automation.
• Experience with scientific and data-processing libraries such as pandas, NumPy and RDKit or equivalent tools.
• Good understanding of statistical analysis and supervised and unsupervised machine-learning methods.
• Familiarity with databases, SQL, APIs and structured or semi-structured data.
• Familiarity with LLMs and their practical application to information extraction, analysis or automation.
• Understanding of structured software development, version control and reusable code.
• Ability to work effectively with complex, imperfect and heterogeneous real-world data.
• Strong analytical, problem-solving and communication skills.
• Background in chemistry, chemical engineering, scientific computing or computational science.
• Familiarity with chemical reactions, crystallisation and liquid‑liquid extraction.
• Experience working with experimental, analytical or high‑throughput datasets.
• Experience with statistical modelling, time‑series analysis, neural networks or deep learning.
• Experience with computer vision, image processing or multimodal models.
• Experience building data pipelines, APIs, internal tools or automated computational workflows.
• Experience extracting structured information from scientific literature or technical documents.
• Experience with LLM tool calling, RAG, AI agents or agentic workflows.
• Experience with laboratory automation, scientific instruments or sensor‑generated data.
• Familiarity with cheminformatics or chemical data.