Experimental physicist · Applied AI

Aditya Kumar

I build processes, AI automation and collaborations that get hard technical work finished.

Six years building processes and systems for experimental physics. Now building the bridge that lets AI use them.

Institute of Physics Johannes Gutenberg University Mainz

View CV Get in touch

Selected work

The lab's literature as a citation map on a dark background: thousands of papers drawn as points in clouds of blue, orange, teal, pink and violet, one colour per research community, with a few highly cited papers labelled by first author and year and lines fanning out from one 2025 paper at the centre to the papers it cites.

Agentic RAG · 2026-present

A lab's literature of more than 10,000 papers, searchable by AI agents with every answer traced to the passage it came from.

Agentic domain-specific RAG

10,000+ papers and theses
0.92 figure Recall@10
0.77 passage Recall@10

A block diagram on a dark ground: three clients, a physicist through a GUI, an AI agent through MCP and a script through a CLI, each connect to one engine that checks every command against limits, role, attendance and a kill switch, which drives a virtual-instruments layer over four instruments: temperature, magnet, source meter, and camera and stage.

Instrument software · 2026-present

Laboratory instruments that a physicist and an AI agent can operate side by side, with every command checked by the same safety rules.

I2AS: Instrument to Agentic Station

2 setups deployed
4 client surfaces, one declaration
4 agent roles

A line drawing of a cryostat, its outer vessel enclosing an inner chamber with a sample at the centre of a magnet bore, marked in maroon. Circuit-board traces run from the cryostat to five stacked instrument icons on the right: a computer display, a gauge, an oscilloscope, a control unit and a meter.

Instrument software · 2024-present

Cryogenic measurements that run for 30 to 40 hours with nobody watching, inside safety limits the software enforces itself.

CryoSoft

30 to 40 h unattended runs
1 week to 2 hours onboarding
6 architecture layers

A schematic on a dark ground. Top row: the SharePoint wiki of 1,027 pages syncs through the Microsoft Graph API, using an Azure AD app registration, into a privacy filter and an OpenSearch index of 2,135 passages from 715 pages. Bottom row: a researcher asks the lab AI chatbot, which calls the MCP tool search_group_wiki, which runs hybrid semantic and keyword search fused by RRF over the index; the answer returns citing the wiki pages. A dashed outline marks the filter, index, tool and search as hosted at the university.

Agentic RAG · 2026-present

The lab's internal wiki answering questions in its AI chatbot, with the right page in the top 10 for 99 of 100 test questions.

Wiki RAG: the lab's know-how on call

1,027 wiki pages synced
0.99 page Recall@10
0.74 passage Recall@1

Two panels on a dark ground. Left: an optical micrograph of the junction with the h-BN, few-layer graphene and CrSBr flakes outlined in yellow, black and blue against a 15 micrometre scale bar, above a three-dimensional cutaway schematic of the same stack with gold contacts. Right: magnetoresistance ratio against bias voltage from minus 1 to plus 1 volt at six temperatures from 20 to 70 K, every curve M-shaped with maxima near plus and minus 0.5 volts.

Research · spintronics

A magnetic tunnel junction with no magnetic electrodes at all, switching its resistance by 350%.

Bias-tunable magnetoresistance in a CrSBr junction, and the mechanism behind it

350% magnetoresistance at 20 K
12 nm magnetic barrier
±0.5 V operating point

Applied AI · 2025-present

Every number pulled out of a paper carries the exact sentence it came from, and a grade for how well that check holds.

TracEx

1 model call per paper
A/B/C verification grade per value
3 model providers supported

See all work →

What I do

AI and Automation

I write the code instruments and AI agents run on. One system runs cryogenic measurements for 30 to 40 hours with nobody watching; another answers from 10,000+ papers, every answer traced to its source.

Fabrication and characterization

Controlling Hardware

I fabricate van der Waals devices and build the measurement chains that read them. One junction, with no magnetic electrodes at all, switches its resistance by 350%.

Management and leadership

Coordinating people

Elected by my peers to run a research pipeline across two universities. I lead my lab's AI taskforce, co-organised two international exchange programmes and supervised three junior researchers.

Recent

Aditya Kumar standing beside the lectern in a wood-panelled lecture hall at the end of his AI4Sci 2026 talk, below a projected closing slide reading Thank you for your attention, with a Kläui Lab group photograph and the logos of the Kläui Lab, JGU and the funding bodies.

October 2026 · Talk

Let's talk

Looking for someone who can move between the lab bench and the codebase, and get a room of people to agree on what to build. The full record is in the CV.