# Machine Learning Engineer — Vitol

- Location: Houston, TX
- Posted: Nov 11, 2026
- Status: open (checked Nov 18, 2026)
- Apply (employer's site): https://jobs.smartrecruiters.com/vitol/744000161144378
- Employer record: https://visajobs.io/company/vitol.md

## Sponsorship history
- Tier: Good history
- Occupation (SOC): Software Developers (15-1252)
- Employer's certified LCAs for this occupation in TX, FY2024–FY2026: 8
- …in the whole US: 8
- With this exact title: 0
- Median DOL prevailing wage, level I / II: $84k / $106k

## Description
Job Description
As our portfolio of work continues to grow, we are looking for an experienced Machine Learning Engineer to join our AI and machine learning team. The individual will work closely with AI, data and machine learning specialists, software engineers and commercial teams to deliver machine learning models and applications. We work across the trading business, operations, and other support functions; so the individual will need to be comfortable working with a variety of stakeholders and technologies. The successful candidate will bring a strong machine learning background and have extended this expertise through hands-on delivery of GenAI projects.
The Machine Learning Engineer at Vitol has visibility and impact across the full project workflow: from working with business stakeholders to help define the project, to data collation and processing, exploratory analysis, model selection and tuning, and implementation of production models.
The successful candidate will join a team of experienced, collaborative practitioners, who are (pragmatically) solving some of the most challenging and impactful problems the energy industry is facing; as well as pushing the boundaries around the ‘art of the possible’.
Core Responsibilities include:
Design, develop, and deploy end-to-end machine learning and data science solutions across our wider business activities (including trading, operations, and support functions) - from raw data ingestion through to production-grade models and monitoring
Drive adoption and development of the firm's internal GenAI platform and applications, extending capabilities through new integrations, data connectors, and domain-specific context engineering; work closely with trading desks and operational teams to identify high-value use cases, embed the tool into day-to-day workflows, and ensure outputs are robust, and trusted by end users.
Design, prototype, and deploy agentic LLM workflows, including tool use and function calling; develop reusable prompts and AI Skills integrated into business workflows
Evaluate and benchmark LLM and agentic solutions, engaging regularly with stakeholders to gather feedback and refine solutions
Apply a broad range of modelling techniques - including time-series forecasting, NLP, classification, and generative AI - to commodity pricing, supply/demand signals, trade flow analysis, and operational optimisation problems
Own the full data science and machine learning lifecycle on assigned projects: data sourcing and cleaning, exploratory analysis, feature engineering, model selection and validation, deployment, and ongoing performance monitoring
Build and maintain robust, well-tested, production-quality code; contribute to shared infrastructure including ML pipelines, data orchestration, and model serving layers
Integrate ML and GenAI outputs into existing trading systems, dashboards, and workflows; work with software engineers to ensure reliable, scalable adoption across the business
Communicate analytical findings and model outputs clearly to non-technical stakeholders; present results, assumptions, and limitations in a manner that supports confident commercial decision-making
Actively participate in code reviews, experiment design, and tooling decisions; mentor colleagues and help raise the overall standard of analytical and engineering practice across the team
Qualifications
Master’s degree or equivalent in Computer Science, Statistics, Mathematics, Data Science, or a related quantitative field
Fluency in Python for both data science and engineering purposes: clean, modular, well-documented code, with strong understanding of software engineering best practices including version control, testing, and code review
5+ years of industry experience developing and deploying machine learning or statistical models, with a proven track record of delivering end-to-end solutions in production environments
Demonstrable experience applying a broad range of ML methodologies (supervised and unsupervised learning, time-series modelling, NLP/LLMs, optimisation) to real-world business problems
Strong proficiency with ML frameworks (e.g. PyTorch, scikit-learn, Transformers) and experience building or consuming LLM-based pipelines and GenAI applications. Hands-on delivery of GenAI projects, including prompt engineering and agentic patterns such as tool use and function calling
Experience with cloud platforms (AWS preferred) and modern MLOps practices: containerisation (Docker/Kubernetes), CI/CD, data pipeline orchestration (e.g. Airflow, Dagster), and model serving
Strong analytical and problem-solving ability: capable of defining and scoping open-ended problems, proposing sound methodological approaches, and defending modelling choices with rigorous reasoning
Excellent written and verbal communication skills, with the confidence to present model outputs, caveats, and commercial implications clearly to non-technical audiences including traders and senior management
Genuine intellectual curiosity about commodities markets, global energy flows, and the commercial dynamics of trading; willingness to develop domain knowledge as part of the role
Desirable Experience
Experience in the energy or commodities trading industry, with knowledge of financial markets and trading concepts
Experience surfacing ML outputs through interactive tools (e.g. Dash, Streamlit, or similar) and presenting use cases to non-technical audiences, including traders and senior management
Time-series modelling in a trading or financial context, including both ML-based and econometric approaches (e.g. ARIMA, cointegration, regime-switching models)
Experience building retrieval-augmented generation (RAG) pipelines or multi-agent systems
Experience building Model Context Protocol (MCP) servers or clients
Data orchestrators (Airflow, Dagster) and cloud-based ETL/ELT pipelines
Prior work on LLM evaluations (evals) or model benchmarking
Personal Characteristics
A self-motivated individual who

> History, not a promise: past H-1B filings do not mean an employer will sponsor you or a given role. Data: U.S. DOL OFLC LCA disclosure (FY2024–FY2026 for role counts, certified LCAs) and the USCIS H-1B Employer Data Hub. Not legal advice. Methodology: https://visajobs.io/methodology
