Lead Data Scientist Los Angeles, United States

Vantora; Los Angeles (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Vantora is seeking a Lead Data Scientist to design, train, and deploy models that turn complex oil and gas data into actionable intelligence. You will work with product, engineering, and domain experts to prototype and productionize AI solutions that influence planning, production, and operations.

You will prototype rapidly across modeling approaches, evaluate performance, and ensure robust data pipelines and reproducibility.

Qualifications

• 6+ years of professional experience in applied data science, ML, or advanced analytics.
• Direct experience applying data science or ML in the oil and gas industry (upstream/midstream/downstream).
• Experience building and deploying models in production, ideally in B2B SaaS, energy tech, or enterprise setting.

Responsibilities

• Design and implement ML models for prediction, optimization and pattern detection across large oil and gas datasets.
• Collaborate with product, engineering, and domain experts to define use cases and translate requirements into quantitative problems.
• Build and maintain data pipelines for scalable model training, evaluation and deployment.
• Prototype rapidly with various modeling approaches (regression, time-series, clustering, RL, deep learning).
• Evaluate model performance with rigorous experimentation and feature engineering.
• Partner with AI/LLM team to integrate predictive and generative components into workflows.
• Communicate findings to technical and non-technical stakeholders and guide decisions.
• Establish best practices for reproducibility, versioning, and documentation.

Skills

Applied ML

Data wrangling

Python

SQL

Model deployment

Cloud pipelines

Experiment design

Communication

Tools

Databricks

Spark

Airflow

TensorFlow

PyTorch

scikit-learn

Job description

About the Opportunity

We're partnering with a global energy leader to reimagine how exploration decisions are made. By combining AI, advanced data science, and complex industrial datasets, we're building a next-generation intelligence platform designed to accelerate discovery, uncover new opportunities, and transform exploration decision-making.

As Lead Data Scientist, you'll be at the core of this effort, designing, training, and deploying models that turn complex, messy, real-world oil and gas data into actionable intelligence. You'll work closely with product, engineering, and domain experts to prototype, validate, and productionize AI solutions that directly impact how our users plan, produce, and operate. This is a hands‑on role for a builder who knows the energy industry, thrives in ambiguity, moves fast from idea to experiment, and loves turning data into real‑world results.

In This Role, You Will

• Design and implement ML models for prediction, optimization, and pattern detection across large, multi-source oil and gas datasets (e.g., production, drilling, reservoir, sensor/SCADA, and asset data).
• Collaborate cross‑functionally with product managers, engineers, data engineers, and oil and gas domain experts to define use cases, collect requirements, and translate operational and business needs into quantitative problems.
• Build and maintain data pipelines that support scalable model training, evaluation, and deployment.
• Prototype rapidly, exploring different modeling approaches (e.g., regression, time‑series forecasting, clustering, reinforcement learning, and deep learning) to find the most effective solutions.
• Evaluate and improve model performance through rigorous experimentation, feature engineering, and error analysis, grounded in the physical and operational realities of oil and gas assets.
• Partner with the AI/LLM engineering team to integrate predictive and generative components into end‑user workflows.
• Communicate findings clearly to both technical and non‑technical audiences, bridging the gap between model outputs and business decisions.
• Establish best practices for reproducibility, versioning, and documentation to support long‑term scalability.

What You Bring

• 6+ years of professional experience in applied data science, machine learning, or advanced analytics.
• Required: Direct experience applying data science or ML in the oil and gas industry (upstream, midstream, or downstream), with a working understanding of operational data such as production, drilling, reservoir, or equipment/sensor data.
• Proven ability to build and deploy models in production, ideally within a B2B SaaS, energy technology, or enterprise environment.
• Expertise in Python, SQL, and common ML frameworks (scikit-learn, PyTorch, TensorFlow, XGBoost, etc.).
• Strong experience with data wrangling, feature engineering, and exploratory data analysis using large-scale structured and unstructured datasets.
• Familiarity with time‑series, forecasting, and predictive maintenance models is a plus.
• Experience with cloud-based ML pipelines (GCP, AWS, or Azure) and data infrastructure tools (Databricks, Spark, Airflow, etc.).
• Ability to design experiments and A/B tests, interpret results, and guide decision-making through data.
• Strong communication and storytelling skills, able to contextualize technical insights for executives, field operations teams, and business stakeholders.

Nice to Have

• Experience at an energy operator, oilfield services company, or energy-focused software/analytics firm.
• Exposure to physics-informed ML or hybrid models that combine engineering principles with data-driven approaches.