Open to opportunities

Rishabh Malik

@rishabhmalik1

Message

Senior data scientist building production ML and LLM systems that cut costs and improve decision-making.

United Kingdom

Message

What I'm looking for

I’m looking for a role where I can ship production forecasting and LLM/RAG solutions on AWS, work closely with SMEs, and deliver measurable business impact with strong evaluation, monitoring, and retraining.

I’m a data scientist with 8 years building production ML and LLM systems, most recently leading forecasting, LLM case classification, and decision-support analytics. At LNER, I cut onboard catering waste by 48% (£200k+ per year) using AWS SageMaker forecasting and shipped delay attribution that flags delays over 20 seconds with evidence for operator delay payouts.

I take responsible ML from proof of concept to production: I deployed LLM case classification in Salesforce Agentforce, reaching 92% accuracy at level 1 and 88% overall with confidence-threshold routing for human review. My current focus is machine learning, LLMs, AWS, and RAG—backed by robust evaluation, scheduled retraining, monitoring, and strong SME collaboration.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist

Current

London North Eastern Railway (LNER)

Oct 2025 - Present (9 months)

Delivered production data science for demand forecasting, LLM case classification, and decision-support analytics, reducing onboard catering waste by 48% (over £200k/year). Built delay attribution to flag delays over 20 seconds across 15M+ train movement records and deployed an LLM classifier reaching 92% accuracy at level 1 (88% overall) with confidence-based routing.

Machine Learning Forecasting AWS Sagemaker Regression Models Scheduled Retraining Amazon RDS SVM Python SQL Data Validation

Data Science Intern

London North Eastern Railway (LNER)

Apr 2025 - Oct 2025 (6 months)

Data Science Intern at London North Eastern Railway (LNER) supporting production analytics work.

Solutions Analyst

London North Eastern Railway (LNER)

Oct 2024 - Apr 2025 (6 months)

Analyzed customer and case data in Salesforce CRM to identify recurring issues and process bottlenecks. Built dashboards from telesales ticket data and Salesforce forecast output for management reporting.

Salesforce Data Analysis Dashboarding Reporting Telesales Forecasting Analytics

System Engineer (Information Security)

DXC Technology

Jul 2021 - Jul 2022 (1 year)

Deployed Matomo analytics and a Grafana/Loki monitoring stack on AWS using Terraform and Helm as infrastructure as code. Automated alert routing into Jira and extended Ansible playbooks to include legacy SUSE 11 servers in the automated pipeline.

Matomo Grafana Loki AWS Terraform Helm Infrastructure as Code Jira Ansible Monitoring CI CD

Codebase RAG Assistant

Independent Projects

Jan 2024 - Present (2 years 6 months)

Built a retrieval-augmented assistant for answering developer questions over a codebase, tuning chunking and comparing chunk sizes and embedding models against an evaluation set.

RAG Embeddings Model Evaluation

Education

Degrees, certifications, and relevant coursework

Newcastle University

Master of Science in Data Science, Data Science

2022 - 2023

Grade: Merit

Activities and societies: 2nd place, university data science hackathon (2023).

Earned an MSc in Data Science (Merit) at Newcastle University from September 2022 to September 2023. Placed 2nd in the university data science hackathon in 2023.