Machine Learning Engineer

Vitol•Houston, TX

5h•Onsite

About The Position

Vitol is seeking an experienced Machine Learning Engineer to join its AI and machine learning team. The role partners with AI, data and machine learning specialists, software engineers, and commercial teams to deliver machine learning models and applications across trading, operations, and support functions. The successful candidate will bring a strong machine learning background and hands-on experience delivering GenAI projects. The position has visibility across the full project workflow, from defining projects with business stakeholders through data collation and processing, exploratory analysis, model selection and tuning, and production implementation. The engineer will develop end-to-end machine learning and data science solutions, advance the firm's internal GenAI platform, and integrate models and AI outputs into business systems and workflows. The role is based onsite in Houston, Texas, five days per week.

Requirements

Master’s degree or equivalent in Computer Science, Statistics, Mathematics, Data Science, or a related quantitative field.
Fluency in Python for data science and engineering, including clean, modular, well-documented code and software engineering practices such as version control, testing, and code review.
At least 5 years of industry experience developing and deploying machine learning or statistical models, with a record of delivering end-to-end production solutions.
Demonstrable experience applying a broad range of ML methodologies, including supervised and unsupervised learning, time-series modelling, NLP/LLMs, and optimisation, to real-world business problems.
Strong proficiency with ML frameworks such as PyTorch, scikit-learn, or 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, including Docker/Kubernetes, CI/CD, data pipeline orchestration, and model serving.
Strong analytical and problem-solving ability, including defining open-ended problems, proposing methodological approaches, and defending modelling choices with rigorous reasoning.
Excellent written and verbal communication skills, including presenting model outputs, caveats, and commercial implications to non-technical audiences such as traders and senior management.
Intellectual curiosity about commodities markets, global energy flows, and trading dynamics, and willingness to develop domain knowledge.
Self-motivated, delivery-focused, and comfortable navigating ambiguity and making judgements under uncertainty.
Methodical and detail-oriented, with rigor in experimental design, data validation, code quality, and documentation.
Resourceful and adaptable in a dynamic environment; collaborative, non-political, and of high integrity.

Nice To Haves

Experience in the energy or commodities trading industry, with knowledge of financial markets and trading concepts.
Experience surfacing ML outputs through interactive tools such as Dash or Streamlit and presenting use cases to non-technical audiences.
Time-series modelling in a trading or financial context, including ML-based and econometric approaches such as ARIMA, cointegration, or regime-switching models.
Experience building retrieval-augmented generation (RAG) pipelines or multi-agent systems.
Experience building Model Context Protocol (MCP) servers or clients.
Experience with data orchestrators such as Airflow or Dagster and cloud-based ETL/ELT pipelines.
Prior work on LLM evaluations or model benchmarking.

Responsibilities

Design, develop, and deploy end-to-end machine learning and data science solutions across trading, operations, and support functions, from raw data ingestion through production models and monitoring.
Drive adoption and development of the internal GenAI platform and applications through integrations, data connectors, and domain-specific context engineering; identify valuable use cases with trading and operational teams and embed tools in workflows.
Design, prototype, and deploy agentic LLM workflows, including tool use and function calling, and develop reusable prompts and AI Skills for business workflows.
Evaluate and benchmark LLM and agentic solutions, gather stakeholder feedback, and refine solutions.
Apply modelling techniques including time-series forecasting, NLP, classification, and generative AI to commodity pricing, supply and demand signals, trade flow analysis, and operational optimisation.
Own the data science and machine learning lifecycle for assigned projects, including data sourcing and cleaning, exploratory analysis, feature engineering, model selection and validation, deployment, and performance monitoring.
Build and maintain robust, well-tested, production-quality code and contribute to shared ML pipelines, data orchestration, and model serving infrastructure.
Integrate ML and GenAI outputs into trading systems, dashboards, and workflows, working with software engineers to support reliable and scalable adoption.
Communicate analytical findings and model outputs to non-technical stakeholders, including results, assumptions, and limitations, to support commercial decision-making.
Participate in code reviews, experiment design, and tooling decisions; mentor colleagues and help improve analytical and engineering practices across the team.

Benefits

Medical coverage
Dental coverage
Vision coverage
Paid vacation
401(k) with company contributions
Life insurance
Short-term and long-term disability coverage
Large diversity of projects with real-world impact
Entrepreneurial environment with a flat hierarchy
Close collaboration with business units across London, Singapore, Houston, and Geneva
Supportive, highly motivated data science and machine learning team
Opportunity to contribute to the energy transition through renewable and alternative energy sources