You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Vitol

Senior Data Scientist, Applied ML

  • Office
  • 6+ years

Salary

Not stated

Similar roles pay $140K - 215K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The Applied ML team in Houston works with the company's trading desks to find commercial value in data using applied data science.

Each project begins with a question from a trader or analyst, and the model comes afterward.

You work with traders and analysts from the first discussion until the tool is live, and you stay with it once it ships.

You are responsible for both the modelling and getting it into production. Work moves in short phases and succeeds only if the desk makes better decisions with it.

You choose your own approach, and the results must be reliable enough for traders to depend on.

The company is one of the world's largest independent energy traders. It produces, manages and delivers energy and commodities worldwide.

Beyond trading, it has $10+ billion invested in long-term infrastructure assets.

Customers include national oil companies, multinationals, large industrial firms and utilities.

Founded in Rotterdam in 1966, the company serves customers from more than 40 offices and reported $343bn in revenue for 2025.

The team includes people from 65+ nationalities.

Houston is one of the company's core trading offices, and the team sits close to the desks, so feedback is quick.

In year one, traders and analysts on at least two desks bring their problems to you directly.

At least two proof-of-value projects reach a go/no-go decision, and at least one runs in production and gets regular use on its desk.

Production models are monitored, documented and supportable by the wider team, so monitoring catches failures before a trader does.

Failed experiments are stopped early and written up so nobody repeats them.

You build reusable components, such as extraction pipelines and evaluation harnesses, for the rest of the team to use.

Responsibilities

  • Partner with traders and analysts to turn market questions into scoped projects, each with a clear commercial hypothesis and a defined go/no-go point.
  • Review progress with the desk during every project, showing early intermediate results, testing them against market knowledge, and changing direction when the signal or priority changes.
  • Build LLM, NLP and multimodal pipelines that pull structured signals out of unstructured sources such as outage reports, news, filings and web content.
  • Run quick feasibility experiments across modelling approaches and end weak ideas early.
  • Develop models that forecast outage impacts, classify disruption patterns, and spot anomalies and regime shifts in fundamental data.
  • Move proven models to production as packaged, tested code shipped through CI/CD, with monitoring and drift detection from the start.
  • Put insights where traders already work, in Teams, alerts, and the desk's Excel and Python tools. Standalone dashboards are not the default choice.
  • Source data through the company's data platform. For a new source, work with that team instead of building separate pipelines, and follow the existing web-scraping architecture.
  • Assess commercial AI platforms and tools against real desk problems and recommend one clearly.
  • Explain results, uncertainty and limitations plainly to traders, analysts and senior stakeholders.

Requirements

  • You have 5+ years applying machine learning and NLP to messy real-world data, including models you have taken to production and supported afterwards.
  • You have worked directly with commercial users in trading, finance or a similar fast-paced setting and can name decisions your work changed.
  • You hold a Master's or PhD in statistics, mathematics, physics or engineering, or have equivalent depth gained in industry, with strong statistics and experimental design skills.
  • You have built extraction and classification pipelines with LLMs, covering evaluation, prompt and retrieval design, and cost and latency trade-offs.
  • You work in Python with scikit-learn, PyTorch and HuggingFace, and write production-quality code that others can review and maintain.
  • You have used Docker, AWS, CI/CD and MLOps practice, including model versioning, monitoring and retraining.
  • You have experience with anomaly detection and with combining signals from multiple time-series and text sources.
  • You can explain what a model means for a trade in two sentences and handle challenges from people who know the market better than you do.
  • Nice to have: knowledge of energy or commodities markets, graph modelling, sentiment analysis, or agentic workflows and MCP.

Conditions

Based in Houston, TX, working onsite 5 days a week.

All your information is kept confidential under EEO guidelines.

Benefits

  • Medical, dental and vision coverage.
  • Paid vacation.
  • 401k with company contributions.
  • Life insurance.
  • Short-term and long-term disability cover.

Where you’d work

From the office

About the company

Vitol

Office in Houston, United States

Also hiring in Geneva, Switzerland and London, United Kingdom

Your chances

We've checked whether it's still hiring and how crowded it is.

  • 19 checks run
  • 0 red flags

Still hiring?

13 checks

No red flags

How crowded?

6 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details11 facts · Role, Location, Compensation, Employment
Tech stack
  • Python
  • AWS
  • Docker
  • PyTorch
  • LLMs
  • scikit-learn
  • NLP
Seniority
Senior
Type
Full-time
Specialty
Data Science
Region
United States
Pay period
Annual
Show 5 more factsShow less

Role

Category
Data & Analytics
Specialty
Data Science
Seniority
Senior
Experience
5+ years
Tech stack
  • Python
  • AWS
  • Docker
  • PyTorch
  • LLMs
  • scikit-learn
  • NLP

Location

Work model
Office
Region
United States
Office
  • Houston, United States

Compensation

Salary
Salary by agreement
Pay period
Annual

Employment

Type
Full-time

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason