💻 Senior Machine Learning Engineer 📍London (Hybrid, 40% in office) 💸 £Salary + Benefits 

Introducing Machine Learning and AI at Trainline 👋 

Machine learning is at the heart of Trainline's mission to help millions of people make sustainable travel choices every day. Our ML models power critical aspects of our platform, including: 

• Advanced search and recommendations capabilities across our mobile and web applications 
• Pricing and routing optimisations to find the best fares for customers 
• Personalised user experiences enhanced by generative AI 
• Data-driven digital marketing systems 
• AI agents improving customer support 

Our machine learning teams own the complete delivery lifecycle from ideation to production. We work closely with stakeholders across the business to expand the understanding and impact of machine learning and AI throughout Trainline. 

The Role

We are looking for a Senior Machine Learning Engineer to join our team help shape the future of train travel. You will be part of a highly innovative AI and ML platform working alongside engineers, scientists and product managers to tackle complex challenges by combining Trainline’s rich datasets with cutting edge algorithms. What unites our team is an expertise in the field, a love of what we do and the desire to create impactful solutions to support Trainline’s goals of encouraging sustainable travel.  

As a part of Trainline you will be joining an environment where learning and development is top priority. You will have the opportunity to work with fellow ML enthusiasts on large-scale production systems, delivering highly impactful products that make a difference to our millions of users.  

As a Senior Machine Learning Engineer at Trainline you will... 🚄   

• Work in cross-functional teams combining data scientists, software, data and machine learning engineers, and product managers  
• Design and deliver machine learning models at scale that drive measurable impact for our business  
• Own the full end to end machine learning delivery lifecycle including data exploration, feature engineering, model selection and tuning, offline and online evaluation, deployments and maintenance  
• Partner with stakeholders to propose innovative data products that leverage Trainline’s extensive datasets and state of the art algorithms  
• Create the tools, frameworks and libraries that enables the acceleration of our ML products delivery and improve our workflows  
• Take an active part in our AI and ML community and foster a culture of rigorous learning and experimentation 

We'd love to hear from you if you...🔍   

• Have an advanced degree in Computer Science, Mathematics or a similar quantitative discipline  
• Are proficient with Python, including open-source data libraries (e.g Pandas, Numpy, Scikit learn etc.)    
• Have experience productionising machine learning models   
• Are an expert in one of predictive modeling, classification, regression, optimisation or recommendation systems  
• Have experience with Spark   
• Have knowledge of DevOps technologies such as Docker and Terraform and ML Ops practices and platforms like ML Flow  
• Have experience with agile delivery methodologies and CI/CD processes and tools  
• Have a broad of understanding of data extraction, data manipulation and feature engineering techniques   
• Are familiar with statistical methodologies.  
• Have good communication skills   

Nice to have 😍 

• Experience with transport industry and/or geographical information systems (GIS)  
• Experience with cloud infrastructure  
• Understanding of NLP algorithms and techniques  and/or experience with Large Language Models (fine tuning, RAG, agents)  
• Experience with graph technology and/or algorithms 

Our technology stack 💻  

• Python and associated ML/DS libraries (scikit-learn, NumPy, LightGBM, Pandas, LangChain/LangGraph, TensorFlow, etc...) 
• PySpark 
• AWS cloud infrastructure: EMR, ECS, Athena, etc.  
• MLOps: Terraform, Docker, Airflow, MLFlow  

We'd love to hear from you if you...🔍  

• Have an advanced degree in Computer Science, Mathematics or a similar quantitative discipline 
• Are proficient with Python, including open-source data libraries (e.g Pandas, Numpy, Scikit learn etc.)   
• Have experience productionising machine learning models  
• Are an expert in one of predictive modeling, classification, regression, optimisation or recommendation system 
• Have experience with Spark  
• Have knowledge of DevOps technologies such as Docker and Terraform and ML Ops practices and platforms  like ML Flow 
• Have experience with agile delivery methodologies and CI/CD processes and tools 
• Have a broad of understanding of data extraction, data manipulation and feature engineering techniques 
• Are familiar with statistical methodologies. 
• Have good communication skills  

Nice to have 😍

• Experience with transport industry and/or geographical information systems (GIS) 
• Experience with cloud infrastructure 
• Understanding of NLP algorithms and techniques 
• Experience with Large Language Models (fine tuning, RAG, agents) 

Our technology stack 💻 

• Python 
• PySpark for processing big data 
• AWS: EMR, ECS, Athena, etc. 
• DevOps: Terraform, Docker, Airflow, MLFlow 

The interview process 🚉 

• Recruiter Call (30 minutes)
• Meeting the Head of ML & AI (30 minutes)
• Technical Interview with 2 x Engineers (90 mins)
• Final Interview (30-45 mins)