Ingeniero / a de Desarrollo - Development Engineer

Nextmol; Madrid; Presencial; EUR 40.000 - 65.000; Jornada completa

Descripción de la vacante

A cutting-edge technology firm in Madrid is seeking an R&D Engineer with a strong background in computational chemistry. The ideal candidate will integrate molecular modeling with data-driven approaches to solve complex scientific problems. Responsibilities include developing machine learning models for property prediction and connecting simulations to accelerate material discovery. A PhD in a relevant field and proficiency in Python are essential. The company values innovation and offers opportunities for continuous learning.

Formación

• Proven experience in machine learning for chemistry applications.
• Experience with polymers and surfactants is highly valued.
• Capacity to adjust to evolving project needs.

Responsabilidades

• Use molecular modeling methods to characterize molecular systems.
• Develop, train, and optimize machine learning models.
• Connect data-driven approaches with molecular simulations.

Conocimientos

Proficiency in Python

Familiarity with cheminformatics frameworks

Machine learning theory and applications

High level of English

Educación

PhD in Chemistry, Physics, or a related STEM discipline

Herramientas

RDKit

Scikit-learn

MDAnalysis

Git

Descripción del empleo

Nextmol is a spin-off company of the Barcelona Supercomputing Center, offering advanced services in Molecular Simulation and Artificial Intelligence applied to chemistry. We are developing a cutting‑edge software platform designed to accelerate the design and discovery of new chemical compounds. Our mission is to support the chemical industry in its green and digital transition, enabling a faster development of sustainable chemicals to achieve a circular economy and climate neutrality, comply with regulatory framework, and meet current consumer demands.

We are seeking an R&D Engineer with a strong background in computational chemistry and a passion for integrating molecular modeling with data‑driven approaches. Candidates should be comfortable navigating interdisciplinary challenges, collaborating with chemists, physicists, and data scientists to bridge molecular modeling and data science, solve complex scientific problems, and deliver innovative solutions.

Key Responsibilities

• Use molecular modeling methods, particularly molecular dynamics (MD), to characterize molecular systems and produce high‑quality datasets.
• Develop, train, and optimize machine learning models for chemical property prediction and structure–property relationship analysis.
• Connect data‑driven approaches with molecular simulations to accelerate property prediction and material discovery via high‑throughput screening.
• Contribute to transitioning research prototypes into scalable, production‑ready solutions for industrial applications.

Education and Experience

• PhD in Chemistry, Physics, or a related STEM discipline.
• Proven experience in machine learning theory and applications for chemistry, e.g., property prediction and structure‑activity relationships.
• Experience with polymers and surfactants (concerning both simulation and data‑driven approaches) is highly valued, but not strictly required.

Technical Skills

• Proficiency in Python and common cheminformatics and ML frameworks (e.g., RDKit, Scikit‑learn, MDAnalysis), with experience using Git.
• Familiarity with scientific computing and numerical methods, and HPC computing environments for large‑scale simulations and model training.

Soft Skills

• Motivation to meet project deadlines and promptly address customers’ needs.
• Capacity to adjust to evolving project needs and dynamic research environments.
• High level of English, both written and oral; ability to contribute to cutting‑edge projects at the intersection of AI and molecular science.

Impact

Work on impactful industrial applications with real‑world relevance.

Join a dynamic, growing company with a collaborative team that values innovation, continuous learning, and personal development.