Hey there, I am

Victor Johnson

AI Engineer with 8+ years of experience delivering production AI, Machine Learning, and Data Engineering solutions, specialising in Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Agentic AI workflows (LangGraph), semantic retrieval, vector search, and automated LLM evaluation.
Experienced designing and deploying enterprise GenAI applications using Azure OpenAI, Azure AI Search, LangChain, LangGraph, LlamaIndex, Databricks, Azure Synapse Analytics, Apache Spark, FastAPI, Python, and SQL with a strong focus on model grounding, enterprise guardrails, and cloud efficiency.
Core: LLMs, RAG, Vector Search, Agentic Systems, LLM Evaluation, Python, Azure, Databricks, Spark, LangChain,LangGraph, MLOps.

England, United Kingdom

LinkedIn GitHub

Tech Stack

Generative AI & Agentic AI

Generative AI
Large Language Models (LLMs)
Agentic AI
AI Agents
LangChain
LangGraph
Azure OpenAI
Prompt Engineering

RAG & Knowledge Systems

Retrieval-Augmented Generation (RAG)
LlamaIndex
Semantic Search
Embeddings
Vector Search
Hybrid Search
LLM Evaluation (RAGAS, DeepEval)
Grounding & Guardrails

Machine Learning & AI

Machine Learning
Natural Language Processing (NLP)
Scikit-learn
PyTorch
Predictive Maintenance
Time Series Forecasting

Data Engineering & Cloud

Azure Databricks
Apache Spark
Azure AI Search
Azure Synapse Analytics
Azure SQL
Apache Airflow
Apache Kafka
Microsoft Azure

Programming & APIs

Python
SQL
FastAPI
REST APIs
Docker
Git

Search & MLOps

Elasticsearch
MLflow
Model Monitoring
Vector Databases
Information Retrieval
CI/CD

Experience

Data Scientist

Jan 2022 — Present

Company - SYMEUS LTD

England, United Kingdom · Hybrid | Industry - Finance

Architected and deployed enterprise Retrieval-Augmented Generation (RAG) solutions using Natural Language Processing (NLP), Azure OpenAI, Azure AI Search, LangChain, LangGraph, LlamaIndex, FastAPI, Azure SQL, and Databricks, reducing manual research effort by ~50% while improving retrieval relevance by 25–35%. Designed and implemented production Agentic AI workflows using LangGraph and Azure OpenAI, orchestrating task-specific AI agents for document analysis, information retrieval, reasoning, and workflow execution to automate repetitive business processes. Designed semantic retrieval pipelines using vector search, embeddings, and hybrid retrieval to improve contextual relevance and grounding for enterprise GenAI applications. Implemented automated LLM evaluation frameworks covering retrieval quality, hallucination detection, regression testing, and response validation using Ragas and DeepEval. Built enterprise knowledge ingestion pipelines using OCR, intelligent chunking, embedding generation, and vector indexing for large-scale structured and unstructured document repositories. Developed machine learning models for financial forecasting, scenario planning, predictive analytics, and business decision support, leveraging statistical modelling and data-driven insights to improve forecasting accuracy and strategic planning.

Data Scientist (Part-time)

Feb 2021 — Dec 2021

Company - SYMEUS LTD

England, United Kingdom · Hybrid | Industry - Finance

Developed Databricks, Azure Synapse Analytics, and Apache Spark pipelines supporting production AI workloads and high-volume data processing. Optimized complex SQL/T-SQL workloads and built KPI dashboards (Power BI, Streamlit).

Data Scientist

Dec 2018 — Dec 2020

Company - Alstom

Bengaluru, India · On-site | Industry - Railways

Built and productionised machine learning models for predictive maintenance, including Remaining Useful Life (RUL), degradation modelling, time-series forecasting, and survival analysis for critical train components, reducing parts wastage by ~15%. Analysed millions of telemetry events daily to detect anomalies, sensor drift, and early failure signals, delivering ~5–10% maintenance cost savings through earlier fault detection. Extended component service life by ~10–15% by improving failure prediction accuracy and optimising preventive maintenance scheduling strategies. Applied Monte Carlo simulations to model equipment failure uncertainty and maintenance scenarios, reducing unnecessary maintenance activities by ~20–30%. Built scalable data preprocessing and feature engineering pipelines with MLflow-based experiment tracking, integrating machine learning model outputs into production decision-support systems for engineering and maintenance teams. Designed and implemented Elasticsearch-based search and indexing solutions to enable efficient querying and retrieval of engineering documentation and operational datasets.

Junior Data Scientist

Dec 2017 — Dec 2018

Company - Alstom

Bengaluru, India · On-site | Industry - Railways

Built enterprise search solutions using Elasticsearch and Python to optimize operational document and metadata retrieval (BM25 relevance scoring, inverted indexes, and NLP techniques) Developed ETL pipelines using Apache Airflow, Apache Spark, and Kafka for high-throughput batch and stream data processing. Automated SAP-based business processes to reduce manual effort and operational overhead.

Data Science Intern

Sep 2017 — Nov 2017

Company - Pi Revolutions

Bengaluru, India · On-site | Industry - Retail Tech

Supported data analysis and automation workflows for NFC-enabled billing kiosks Performed exploratory analysis to support process improvements

Intern

Aug 2016 — Sep 2016

Company - Alstom

Bengaluru, India · On-site | Industry - Railways

Automated routine business processes using VBA in Excel, ensuring compliance with internal data standards and improving efficiency, which saved more than 10 hours of reporting work each week