科学软件工程师

The Scientific Software Engineer is responsible for building, extending, and delivering the library of fundamental models that powers Virtual Jar and the Decision Blue platform, which help water-treatment plants optimize the coagulants and chemistry they buy from us. These models predict organics removal, turbidity, disinfection-byproduct formation, pH, and chemical cost across a plant's treatment train. This role turns the underlying science into production-ready code in our repositories, where the platform leverages it to give clients a scientifically sound optimization experience.
At its core this is a delivery role—the primary output is well-built, well-tested model code that ships—but it demands genuine water-treatment fluency, because this person is the bridge between the science and the software, translating subject-matter direction into models that hold up in production. The work directly positions Virtual Jar and Decision Blue to meet clients' water-optimization needs and grows the platform into the processes closely adjacent to coagulation, including pre-oxidation, adsorption, filtration, and charge neutralization. The model library's priorities, scope, and subject-matter direction are owned by the Digital Solutions team; this role sits on the execution and delivery side and owns building, extending, polishing, and managing the models in code.
RESPONSIBILITIES
Model Development & Delivery: Build, extend, and polish the library of fundamental models behind Virtual Jar's coagulation train—organics/UV254, turbidity, pH and coagulation chemistry, and related pre-oxidation, adsorption, and filtration effects—delivering new model versions and new model types into the repositories in Python.
Scope & Requirements Collaboration: Work from scope and requirements set by the Digital Solutions team, collaborating with them to refine and pressure-test those requirements before and during development.
Modeling & Engineering Rigor: Bring literature-grounded functional forms, calibration, hold-out validation, parameter discipline, honest uncertainty reporting, and production-quality code within a Git workflow.
Adjacent Process Expansion: Continue developing optimization models across coagulant and adjacent treatment processes, using an established and evolving scientific basis to expand our offering—organic-polymer coagulants; filtration (conventional, membrane, and bioactive); pre-oxidation effects (ozone, permanganate, peroxide); and adsorption (PAC/GAC).
Software Implementation Support: Work with software development engineers to implement models safely, covering model specs, calibration and validation, performance, and documentation.
Regulatory Modeling Partnership: Partner with other subject-matter experts to fold regulatory drivers into the models—TOC removal requirements, SUVA-based alternative compliance, DBP rules, and more.
QUALIFICATIONS
The successful candidate will have genuine water-treatment domain fluency centered on coagulation and the treatment train, paired with strong Python engineering, and the ability to bridge the science and the software by translating subject-matter direction into well-built, well-tested, production-ready model code.
Specifically, the candidate should have:

• Water-treatment domain fluency centered on coagulation and the treatment train; coagulant behavior, NOM/organics removal, DBP formation, oxidation, and filtration.

• A degree in chemical, environmental, or civil engineering, or equivalent applied depth. This expertise is the essential bridge, even though the core deliverable is code.

• Strong Python engineering, with the ability to build, test, document, and ship model code in a Git workflow.

• Scientific modeling discipline, including calibration, validation, parameter control, and reporting.

• Exceptional communication, with the ability to hold a highly technical conversation about the subject matter with scientists, engineers, and developers alike. Collaboration is central to this role; it is not a heads-down seat.

• The judgment to flag feasibility or other concerns early, and the initiative to help scope the work needed to resolve them.

• Willingness to travel occasionally (approximately 10%).

PREFERRED

• Applied or published experience with coagulation, NOM/organics, ozonation, adsorption, or filtration modeling.

• Familiarity with statistical/ML methods as one tool alongside physically-grounded models.

• Experience translating research models into deployed software.

USALCO is an equal opportunity/affirmative action employer. All qualified applicants will receive consideration for employment without regard to sex, gender identity, sexual orientation, race, color, religion, national origin, disability, protected veteran status, age, or any other characteristic protected by law. As a general policy, USALCO does not offer employment visa sponsorships upon hire or in the future.


Originally posted on Himalayas