Berry Yield Forecaster - EUROPE in Newport

The Organisation

Bitwise Agronomy is a scale-up operation offering farmers operational insight using automated crop analysis via computer vision. We aim to merge modern leading technologies with agriculture to enable farmers to make better management decisions due to more accurate yield forecasting, while also reducing operational costs, increasing productivity and fostering good quality crops. Bitwise Agronomy works globally and as such flexibility is required to accommodate various hours of work across a range of time zones.

Position Context & Purpose

• Translate complex data sets, including growing degree days, temperature, fruit counts, solar radiation, and other relevant variables, into accurate and actionable yield predictions.
• Fix the data. Profile new datasets, find the quality problems, and either fix them or flag them loudly.
• Make the work reproducible. Write queries and scripts someone else can rerun next quarter without you in the room.
• Communicate the result. Turn analysis into a one-pager, a chart, or a five-minute explanation a non-technical stakeholder can act on.
• Be an interface with our customers, leading agronomic/technical discussions, interpreting their needs, and refining forecasts based on their valuable inputs.
• Actively contribute to the growth and success of Bitwise Agronomy by supporting continuous improvement and effectively participating as a member of the team.

Key Accountabilities

• Agronomy
• Hands-on experience in commercial berry production.
• Strong understanding of the key drivers influencing crop yield (e.g., growing degree days, temperature, solar radiation, fruit development).
• Strong understanding of agronomy practices across in commercial berry farms.
• Data
• Confident with pivot tables, lookups (XLOOKUP / INDEX-MATCH), conditional aggregation (SUMIFS, COUNTIFS), data validation and named ranges.
• Can build a model another person can open, follow and audit — inputs separated from calculations, assumptions documented.
• Familiar with Power Query (or equivalent) for repeatable imports and transformations.
• Knows when a spreadsheet is the wrong tool, and says so.
• Python (or R) pandas for cleaning, reshaping and joining data; numpy for the numeric work.
• Reads and writes CSV, Excel, Parquet and JSON, and can pull data from a REST API.
• Works comfortably in notebooks, but can also write a plain .py script that runs on a schedule.
• Familiar with scikit-learn or stats models for regression and forecasting.
• Statistics and modelling
• Solid descriptive statistics, and the judgement to know when the mean is misleading.
• Understands sampling, bias, correlation vs causation, and confidence intervals.
• Can run and interpret a hypothesis test or an A/B comparison.
• Linear and logistic regression — fit one, and explain what the coefficients mean in plain English.
• Knows when not to model, and will say “the data can't answer that.”
• Other Data Skills
• Apply agronomic knowledge and data science principles and techniques to enhance the accuracy and reliability of yield forecasts.
• Drive the agronomy and forecasting narrative during customer discussions, effectively communicating forecasting methodologies, results, and ensuring a clear and shared understanding.
• Actively listen to customer feedback, including insights from agronomists and operational leads, and integrate this information into forecast adjustments.
• Maintain a keen eye for detail in data analysis, model validation, and report generation.
• Effectively communicate technical information to both technical and non-technical audiences.
• Other duties as directed.
• Working with AI tools
• We expect this person to use AI tools as part of normal work, and to use them well.
• Uses an assistant such as Claude, ChatGPT or Copilot day to day to draft and debug code, explain unfamiliar SQL or libraries, scaffold an approach to a problem, translate between languages, and write documentation.
• Writes good prompts — supplies the schema, the constraints and a sample of the data rather than asking a vague question.
• Verifies everything. Runs the code, checks the numbers against a known total, and never pastes an AI-generated figure into a report without confirming it.
• Understands that a confident answer can still be wrong.
• Uses AI to get up to speed on an unfamiliar technique, then genuinely understands it — not a black box they can't defend in a meeting.
• Applies judgement about what data goes into which tool, and follows our data-handling policy.
• Customer Relations
• Work collaboratively with Bitwise customers to enable them to understand the value in their data.
• Respond to customer technical queries and concerns about the forecasts as appropriate in a timely and efficient manner.
• Together with the Customer Success Manager, build and maintain relationships with the stakeholders to ensure the resolution of data issues and queries in a timely manner.
• Work and consult with management and team members across a range of projects to meet business goals and objectives.
• Other duties as directed.

Position Requirements

Qualifications

• Bachelors or Masters’ degree in Agronomy, Agricultural Science, Data Science, Statistics, and/or a related field is preferred.

Experience / Knowledge

• Hands-on experience in commercial berry production.
• Strong understanding of the key drivers influencing crop yield (e.g., growing degree days, temperature, solar radiation, fruit development).
• High level of proficiency in Google Sheet/Microsoft Excel and python.
• Experience in using Python and AI tools (such as Claude) for data analysis and model development.
• Experience in crop yield forecasting is highly desired.

Skills & Abilities

• Fluency in English is essential, it does not need to be the primary language of the successful application, but proficiency is critical.
• Excellent communication, presentation, and interpersonal skills, with the ability to confidently lead customer meetings.
• Strong analytical and problem-solving abilities with meticulous attention to detail.
• Ability to listen actively and interpret information from diverse stakeholders.
• Flexibility to work across a range of time zones, and therefore a variety of hours of work.
• Being adaptive and comfortable working in a fast-paced, evolving environment.