Job Description

At H&P, our people are our strength.

As a P1 hire, you will rotate across multiple AI projects, contributing hands-on to data pipelines, models, and prototypes while learning the drilling domain from SMEs.

What You'll Do

• Build and maintain data pipelines that transform raw one-second sensor data into analysis-ready datasets (drilling events, stand-level aggregations, contextual joins with BHA, survey, and mud data)
• Develop, test, and iterate on machine learning models for time-series problems: anomaly detection, failure prediction, dysfunction classification, and performance benchmarking
• Support retrieval and LLM-based workflows : embedding pipelines, text-to-SQL over drilling related data model, and evaluation of agent outputs.
• Create dashboards, visualizations, and internal tools that make model outputs usable by field engineers and ROC operators
• Perform exploratory analysis to answer engineering questions
• Write clean, documented, version-controlled code and contribute to model monitoring once projects reach production
• Participate in stakeholder interviews and requirement sessions with SMEs and translate field pain points into technical tasks.

What You'll Bring (Required)

• Bachelor's degree in Data Science, Petroleum/Mechanical Engineering, or a related quantitative field (0–2 years of experience; strong internship / professional analyst experience)
• Solid Python fundamentals, including pandas/NumPy and at least one ML framework (scikit-learn, XGBoost, Langchain)
• Working knowledge of SQL and comfort querying large relational datasets
• Understanding of core ML concepts: supervised learning, cross-validation, feature engineering, and evaluation metrics
• Ability to communicate analytical findings clearly to non-technical audiences
• Curiosity about industrial operations and willingness to learn drilling domain concepts (ROP, MSE, DvD, BHA, flat time) on the job.

Nice to Have

• Exposure to time-series analysis or sensor/IoT data
• Experience with cloud data platforms (Microsoft Fabric, Azure, Databricks, or Snowflake)
• Familiarity with LLM application patterns: RAG, embeddings, vector databases, prompt engineering, or agent frameworks
• Dashboarding experience (Power BI, Plotly or React-based tooling)
• Prior internship or project in energy, manufacturing, or another heavy-industrial domain
• Git-based collaboration and basic CI/CD awareness

Why Join

You'll work at the intersection of AI and heavy industry. You will get the opportunity to work on a defined roadmap spanning quick wins to advanced autonomy, and a team culture that pairs new hires with experienced SMEs and data scientists. Few early-career roles offer this breadth: real-time systems, classical ML, and frontier LLM applications inside a single position.

Thank you for your interest in joining our team!