About

Arxada is a global leader in microbial control, committed to solving the world’s toughest preservation challenges through cutting-edge science. We aim to help our customers develop more sustainable solutions that protect and maintain the health and wellbeing of people, extend the life of vital infrastructure, and work to reduce ours and our customers’ ecological footprint. We are seeking a Data Scientist with a strong background in chemistry or biological sciences to support our R&D team’s artificial intelligence platform development. The successful candidate will be responsible for transforming complex microbiological data into a standardized digital format, and building dashboards to interact with the data, with suitability for artificial intelligence platform usage. Role Summary We are seeking an AI scientist who can collaborate closely with a data scientist to design, build, and deploy AI/ML modules that accelerate biocide formulation development, improve predictive decision-making (e.g., stability, efficacy, compatibility), and shorten lab iteration cycles. This role sits at the intersection of formulation chemistry/microbiology, experimental design, and data/AI-driven R&D. You will own end-to-end problem framing, data readiness (with LIMS/ELN), model-user requirements, and lab validation of AI outputs—turning models into actionable tools for bench scientists. Key Responsibilities AI/ML Module Co-Development Convert business/scientific questions into model requirements (e.g., predict stability phase separation, viscosity drift, microbial kill under specific conditions, raw-material compatibility, cost/COGS optimization). Specify and prioritize features/inputs (formulation composition, physical-chemical properties, process parameters, storage conditions, raw-material attributes). Partner on model selection & validation (regression/classification, Bayesian optimization, active learning, multi-objective optimization). Define acceptance criteria (accuracy, applicability domain, explainability). Lead lab validation loops: design confirmatory experiments, refine datasets, and iterate with the data scientist. Work with Data Scientists to generate high-quality datasets for model training/validation. Define and develop code to utilize LLMs to optimize for target product profiles (efficacy, stability, cost-in-use, sensory, compatibility, sustainability constraints). Translate lab findings into mechanistic and statistical insights that inform model features and constraints. Support deployment of user-facing tools (dashboards, notebooks, apps); ensure interpretability and ease of adoption. Data Readiness & Governance Define metadata schemas for formulations, processes, and test methods; ensure data lineage and versioning. Collaborate with IT/data engineering on pipelines from ELN/LIMS to analytics platforms (e.g., Azure ML/Databricks/Power BI). Cross-Functional Influence & Change Management Train and coach bench scientists on using AI tools in everyday formulation work. Create clear communication artifacts (model cards, SOPs, one-pagers, and decision trees). Drive efficiency where AI can eliminate iterations, reduce time-to-lab, and de-risk scale-up. Minimum Qualifications MS/PhD in Chemical Engineering, Chemistry, Materials Science, Pharmaceutical Sciences, or related; or BS with 7+ years relevant experience. 3–5+ years in formulation development (biocides, preservatives, antimicrobials, or adjacent fields such as HI&I, coatings, personal care, agrochemicals, pharmaceutical development). Strong experimental design/DoE and statistical analysis skills (JMP, Design-Expert, R, Python, or similar). Demonstrated experience collaborating with data scientists on predictive modeling and/or optimization projects. Proficiency with ELNs/LIMS and data hygiene—able to structure datasets for modeling and ensure reproducibility. Preferred Qualifications Cheminformatics/QSAR/QSPR familiarity (e.g., molecular descriptors, RDKit) and property estimation. Exposure to Bayesian optimization, active learning, or multi-objective optimization for formulations. Experience with model interpretability (SHAP/feature importance) and applicability domain. Hands-on experience with Azure ML, Databricks, or similar ML platforms; dashboarding with Power BI / other. Background in chemistry Knowledge of sustainability-by-design (biobased actives, VOC limits, hazard/risk assessment). Core Competencies Scientific Rigor & Problem Framing: Converts vague needs into testable hypotheses and model-ready requirements. Data Literacy: Interprets model metrics, understands overfitting, and knows when to trust vs. test. Collaboration & Influence: Bridges R&D, Regulatory, Data Science, and Operations. Execution & Ownership: Bias to action; closes the loop from model insight to validated lab outcome. Adaptability & Learning Agility: Comfort with rapid iteration and evolving toolchains. The expected salary range for this role is 55.000$ - 70.000$, but specific employee compensation may vary depending on factors including experience, education, training, licensure, certification, location and other job-related, non-discriminatory factors permitted by law. This role is also eligible to earn a short-term incentive bonus and the following benefits: 401(k) plan, medical, dental, vision, life, and disability insurance, paid time off, paid holidays and paid sick leave. US01