Subash Ale Magar

Data Engineer · AI & Data Architecture

Cologne, Germany

Building the systems behind useful AI.

I’m Subash, a Data Engineer with a background in data science. I design and develop semantic services, data platforms, and model services that support practical AI applications.

Find your starting pointGet in touch

Search a small universe of ideas

Explore how related ideas can come together. Try a search or choose an example below.

This interactive demo needs JavaScript.

600 points in five topic neighbourhoods. Hover, click, or tap a point to read it.

Search or pick an example. The eight nearest neighbours appear here, closest first.

An interactive illustration of semantic search, using synthetic data and simulated matching.

Currently at LexisNexisSemantic searchAgentic applicationsModel serving & MLOps

A guided visit

A portfolio shaped around your curiosity.

Whether you’re hiring, looking to collaborate, or simply curious, choose a starting point and explore at your own pace.

Guided browsing with prepared content. Live AI is not connected.

Getting your guided visit ready. You can also browse the projects and experience below.

Selected work

Projects and contributions.

A selection of team projects at LexisNexis, with a closer look at my contribution.

Search services and infrastructure

Semantic search for patent data

Helping applications find related patent information by meaning. My contribution spans vector ingestion, search APIs, deployment, and operations, working alongside colleagues across the service.

Python / FastAPIQdrantDatabricksAWS / Kubernetes
Problem & approach

Problem. Patent terminology varies. Applications need a reusable way to retrieve related information by meaning, alongside existing search approaches.

Design. Separate model inference, vector ingestion, and search APIs so that consumers can reuse the capabilities and components can evolve independently.

Operations. Deployment, access controls, observability, and keeping the service reliable as usage grows.

Applications

Agentic AI applications

As part of the team delivering agentic applications, I connect language models with tools, retrieval, and enterprise data.

Problem & approach

Problem. An agent needs access to the right information and tools to complete a useful workflow. Model responses alone are only part of the application.

Contribution. My contribution connects data, retrieval, and AI services with the capabilities people use in the application.

Focus. Reusable service interfaces and clear boundaries between the agent, its tools, and underlying data systems.

Model operations

Inference on Databricks

My work on Databricks connects embedding models with application and data workflows, as part of our wider model-serving effort.

Problem & approach

Problem. Embedding models must support both data processing and application requests, with repeatable deployment and evaluation.

Implementation. My contribution includes developing inference capabilities and integrating them with embedding pipelines and downstream services.

Operations. My work includes MLOps processes for evaluating and maintaining model-based capabilities.

Knowledge & retrieval

RAG & knowledge graphs

My work spans retrieval-augmented generation and knowledge graphs, connecting AI applications to patent information and its relationships.

Problem & approach

Problem. Similarity retrieval finds related content, while some questions depend on explicit entities, relationships, and source evidence.

Approach. I work on combining retrieval with structured knowledge, with interests in patent claims, data linkage, and AI access to enterprise information.

Scope. This is ongoing work; I distinguish research and prototypes from delivered application capabilities.

Experience

A foundation across disciplines.

Software development, data science, and now data engineering.

Feb 2023 — PresentBonn, Germany

LexisNexis

Intellectual Property Solutions

Data Engineer · Previously Data Scientist III

I work across semantic-search design, implementation, and operations within the team, alongside contributions to agentic applications, Databricks model inference, RAG, and knowledge graphs. Earlier projects include patent matching, graph-based patent family creation, and custom classification.

Apr 2021 — Jan 2023Cologne, Germany

nextmarkets

Data Scientist

I worked with colleagues on Azure and Databricks lakehouse platforms, data pipelines, and analytics for internal teams. My contributions also covered risk assessment automation, client scoring, and fraud detection.

Apr 2019 — Mar 2021Passau, Germany

University of Passau

Research Assistant & Developer

I developed interactive applications and OCR workflows with research colleagues, and supported teaching in information retrieval, database systems, and web science.

Earlier experienceNepal & Germany

Software development & systems

Web Development · System Administration

My earlier roles covered websites and business applications using PHP, JavaScript, Java, and databases, alongside system administration and support. These experiences gave me a practical foundation in software and infrastructure.

About me

Curious about data.
Thoughtful about systems.

My career has grown from software development and systems administration into data science and data engineering. I bring those perspectives together when designing AI capabilities that fit the systems and people around them.

I value clear responsibilities and shared problem-solving: understanding the need, weighing the trade-offs, and staying involved from design through operation. I enjoy learning from colleagues and making complex ideas easier to discuss.

Originally from Nepal and now based in Cologne, I hold a master’s degree in Computer Science from the University of Passau, with a focus on data science, machine learning, and text mining.

Education

MSc Computer Science · University of Passau
BSc Computer Science · Pokhara University

Community

My volunteer work has included website development for Apnups in Uganda and humanitarian initiatives with Nyayik Sansar in Nepal.

Data & infrastructure

Python · SQL · PySpark · Databricks
Azure · AWS · Data pipelines

AI & retrieval

Machine learning · Model serving · MLOps
Semantic search · RAG · Knowledge graphs

Services & delivery

FastAPI · Vector databases · Kubernetes
Architecture · CI/CD · Observability

Contact

Let’s connect.

If you’d like to discuss a project, explore a collaboration, or ask about my work, I’d be glad to hear from you.

LinkedIn