Principal Engineer, Operational Intelligence

The ASR Group family of companies make up the world's largest refiner and marketer of cane sugar. The companies produce a full line of grocery, industrial, foodservice and specialty sweetener products. Across North America, ASR Group companies operate five sugar refineries, located in California, Maryland, Louisiana, Canada and Mexico. In Europe, ASR Group companies operate sugar refineries in the United Kingdom, Portugal, and, with a joint venture partner, Italy. The companies also farm sugarcane and own sugar mills in Mexico and Belize. The ASR Group portfolio includes the leading brands Domino, C&H, Florida Crystals, Redpath, Tate & Lyle, Lyle's, Sidul and Whitworths. ASR Group companies also produce and market Tellus, a single-use, compostable tableware and foodservice product made from plant fibers, including sugarcane.

OVERVIEW

The Principal Engineer, Operational Intelligence provides enterprise leadership for the Operational Intelligence discipline across ASR Group refinery operations. The role is responsible for transforming operational information into insights, recommendations, predictions, and actions that improve refinery performance. This position establishes the strategy, standards, governance, technology roadmap, and technical direction for the discipline, which for the purposes of this document means analytics and data science, process and performance intelligence, predictive and prescriptive analytics, optimization, decision support, and operational performance modeling.

Operational Intelligence output is advisory by default. Where an analytical result is to be applied automatically, the write path is designed and owned by Controls under Management of Change. This role is accountable for ensuring intelligence solutions are focused on measurable operational value and support reliable, resilient, secure, and stable refinery operations.

DETAILED ROLES & RESPONSIBILITIES

• Provide enterprise leadership and capability ownership for the Operational Intelligence discipline across refinery sites.
• Develop and maintain the Operational Intelligence strategy, standards, technology roadmap, architecture, and governance model.
• Own the enterprise Operational Context Standard: the asset model, measurement vocabulary, semantic classification of process points, engineering units, naming conventions, and metadata quality expectations that make refinery data usable for analysis. Specify this standard as a data contract that EIC and OT Infrastructure implement in the platforms they own.
• Establish and chair the Operational Intelligence governance forum, with a published intake path for operational problems, a prioritization method, a decision cadence, and a defined escalation route to the Sr. Director, Digital Transformation, OT & Controls when discipline priorities conflict.
• Lead, coach, and develop the central team; set priorities, review technical quality, support skill development, and build a sustainable talent pipeline across the central team and site-based analysts.
• Partner with refinery and functional leaders to identify, prioritize, and define high-value operational problems that can be addressed through the discipline.
• Translate operational needs into a governed portfolio of intelligence initiatives with clear objectives, ownership, value measures, and adoption plans.
• Lead the development, deployment, and sustainment of performance analytics, predictive capabilities, optimization opportunities, decision-support tools, and operational performance models.
• Define and own the production lifecycle for deployed intelligence solutions: where each solution executes, who monitors it, how model drift and data-quality degradation are detected, who responds when it fails, and the criteria for retiring it.
• Own the Operational Intelligence evaluation standard. Analytical and AI outputs are validated against held-out test sets that are not used for tuning, and accuracy, error, and fault rates are measured and published. The discipline is measured on the rate of confident but incorrect output, not only on system availability.
• Establish the enterprise position, jointly with Cybersecurity and Information Technology, on where analytics compute runs relative to the OT and IT boundary, what operational data may leave a site or a region, and the approved use of third-party and cloud artificial intelligence services.
• Own the build-versus-buy standard and the technical recommendation for Operational Intelligence platforms and tools within the approved enterprise architecture; evaluate vendors, run proofs of value against defined acceptance criteria, and manage the resulting supplier relationships.
• Build effective working relationships with Operations, Engineering, Maintenance, Reliability, EIC, Controls, Infrastructure, Cybersecurity, Information Technology, Finance, and other enterprise functions.
• Ensure analytics and AI initiatives follow approved data, security, architecture, lifecycle, validation, documentation, and governance expectations.
• Establish methods to measure the operational and financial value delivered by intelligence initiatives, with benefit baselines set before deployment and post-implementation value verified with Finance.
• Guide the responsible use of artificial intelligence as an enabling tool within Operational Intelligence rather than as a separate organizational discipline.
• Lead the Operational Intelligence Community of Practice to promote knowledge sharing, common methods, reusable solutions, skill development, and enterprise consistency.
• Provide technical and business guidance for data quality, operational context, model performance, solution sustainment, and adoption by refinery users.
• Coordinate with EIC, Controls, and OT Infrastructure within the discipline boundaries and joint ownership defined under Discipline Scope.
• Communicate portfolio performance, risks, decisions, business value, and roadmap progress to senior leadership and refinery stakeholders.
• Travel to manufacturing sites, vendor facilities, and project locations as required to understand operating needs, support deployment, and strengthen adoption.

DISCIPLINE SCOPE

Owns

• Analytics and data science; process and performance intelligence; predictive, advanced, and prescriptive analytics; optimization; decision support; operational insights; artificial intelligence applications; and operational performance modeling.
• The enterprise Operational Context Standard: asset and measurement models, semantic classification of process points, engineering units, naming conventions, and the data quality expectations that analytics depends on.
• The evaluation standard for analytical and artificial intelligence output, including held-out validation, published accuracy and fault rates, and acceptance criteria for production release.
• The production lifecycle of deployed intelligence solutions, including monitoring, drift detection, sustainment, and retirement.

Owns Jointly With EIC and OT Infrastructure

• Operational Intelligence specifies the context, quality, engineering units, sampling, and retention that operational data must meet. EIC and OT Infrastructure implement those requirements in the SCADA, historian, and infrastructure platforms they own. Conflicts are resolved in the Operational Intelligence governance forum and escalate to the Sr. Director, Digital Transformation, OT & Controls.
• Where an intelligence solution is delivered to operators through a plant visualization platform, Operational Intelligence owns the analytical logic, the operational vocabulary, and the correctness of the answer; EIC owns the platform, the visual standard, and the operator experience. Every such solution has a single named product owner drawn from one of the two disciplines.

Key Boundaries

• Does not own SCADA, Ignition, HMI, historians, alarm management, dashboards, reporting platforms, PLC/DCS/SIS logic, instrumentation, electrical systems, or OT infrastructure. The role partners with the owners of those capabilities to use governed operational data effectively.
• Operational Intelligence output is advisory by default and the discipline does not write to control systems. Where an analytical result is to be applied automatically, the write path is designed, implemented, and owned by Controls under Management of Change, with functional safety review where the loop is safety related.

Enterprise Standards, Site-Local Deployment

• Methods, standards, evaluation practice, and architecture are enterprise-wide. Models, asset vocabularies, and deployments are site-specific. Equipment names, measurement terminology, and process meaning differ materially between refineries, and a term must not be merged into a single global model where doing so changes what it means at a site.

WORK EXPERIENCE

• Progressive leadership experience in industrial analytics, data science, process intelligence, operational technology, manufacturing technology, process optimization, engineering, or a related discipline.
• Demonstrated experience leading or mentoring data scientists, analytics professionals, engineers, or cross-functional technical teams.
• Experience converting manufacturing or operational problems into analytic use cases and measurable business outcomes.
• Experience developing, deploying, validating, and sustaining predictive analytics, optimization, decision-support, or AI-enabled solutions in a production operating environment.
• Experience with industrial time-series data at scale, including process historians and operational data infrastructure such as PI or AVEVA, MQTT and Sparkplug, or equivalent, and with ISA-95 or Unified Namespace style asset modeling.
• Experience defining data and context requirements and holding platform owners accountable to them in an organization where the analytics function does not own the platforms.
• Experience combining statistical methods with first-principles process understanding, including mass and energy balance, thermodynamics, and reaction or crystallization behavior, is strongly preferred.
• Experience working with operational data and partnering with Operations, Engineering, Maintenance, Reliability, Controls, and Information Technology teams.
• Experience establishing standards, roadmaps, governance, reusable methods, and a prioritized portfolio of analytics initiatives.
• Experience in refinery, milling, commodity processing, industrial chemical processing, food manufacturing, or another continuous or batch process environment is preferred.

EDUCATION REQUIREMENTS

• Bachelor's degree in Engineering, Data Science, Computer Science, Statistics, Applied Mathematics, Industrial Engineering, Chemical Engineering, or a related technical field from an accredited university.
• Preferred Master's degree or equivalent advanced experience in analytics, data science, engineering, operations research, artificial intelligence, or a related discipline is desirable.

ESSENTIAL CAPABILITIES (KNOWLEDGE, SKILLS, ABILITIES AND PERSONAL ATTRIBUTES)

• Enterprise leadership with the ability to connect analytics and data science to refinery priorities and measurable operating outcomes.
• Strong knowledge of industrial analytics, statistical methods, predictive modeling, optimization, artificial intelligence, and decision-support practices.
• Ability to understand manufacturing processes, operational constraints, data context, and the practical requirements for deploying solutions in operating environments.
• Ability to lead a small expert team while personally shaping strategy, portfolio priorities, stakeholder relationships, and technical quality.
• Sound judgment about the limits of a model and its data, including the discipline to withhold an answer the data does not support rather than present a confident but unsupported result.
• Strong governance, risk management, problem-solving, prioritization, and decision-making skills.
• Excellent written and verbal communication skills, including the ability to explain complex analytical concepts to executive, operational, and technical audiences.
• Demonstrated ability to lead through influence, build trust, and drive adoption in a matrixed organization, including securing sustained change from teams that do not report to this role.
• Commitment to data quality, model validation, cybersecurity, reliability, responsible AI, documentation, and sustainable solution ownership.
• Willingness and ability to travel across manufacturing sites and other business locations as required.

We are an equal opportunity employer. We do not discriminate on the basis of race, color, creed, religion, gender, sexual orientation, gender identity, age, national origin, disability, veteran status or any other category protected under federal, state, or local law. All employment is decided on the basis of qualifications, merit, and business need.