Skip to content
VVS

Software EngineerAI infrastructure and systems researchEdinburgh, UK

VidhunVijayakumar Suja

I build complex systems and then take them apart to see what actually matters. Lately that means an LLM serving engine written from scratch, a controller that tries to tune it while it runs, and an SMT-based checker for weak memory models.

I care about measuring carefully and about saying exactly how far a result goes. MSc Software Engineering from Heriot-Watt, with three manuscripts under review.

  • 01LLM inference and serving
  • 02Adaptive runtime control
  • 03Weak memory and concurrency
  • 04SMT and Isabelle/HOL
  • 05Distributed backends
Fig. 0A miniature inference server, running in your browser
01Router02Scheduler queue03Running batch04GPU step05Outputchat1waitinglong ctx2waitingshared prefix0waitinglast: #6 → chat06Paged KV cache36/48 blocksdecode stepprefill 0 tokdecode 3 seq#4long ctx · 236 tok#5long ctx · 188 tok#6chat · 46 tok#1decode13/15 · 16b#2decode10/12 · 17b#3decode10/19 · 3bAnimated diagram of a miniature LLM serving engine

Hover or tab to a request to see its KV blocks. Click empty space to send one.
Requests are routed by prompt type, admitted into a continuous batch when KV blocks are free, prefilled in chunks alongside running decodes, and stream tokens until done. Shared system prompts reuse cached prefix blocks (hatched). This is a teaching model of the ideas inside Mini-vLLM; its timings are made up.Simulated
Focus
LLM serving, adaptive runtime control, weak memory verification
Education
MSc Software Engineering, Heriot-Watt. Dissertation graded Exceptional (78/100)
Research
Three manuscripts under review: MLSys, TACAS and FSEN 2027
Experience
Research software engineering intern, retrieval and RAG, Dec 2023 to Aug 2024
01About

From retrieval pipelines to memory models

I studied computer science in Kerala, then spent eight months as a research software engineering intern on a five-person team building retrieval systems. That is where I learned that the interesting failures live in the plumbing: a reranker that dominates p95 latency, or an ingestion job that duplicates records after a crash.

At Heriot-Watt I took concurrency and formal methods seriously for the first time. My dissertation became a tool for stepping through executions under WEAKEST, a memory model that is as permissive as possible while still ruling out values that appear out of thin air. That tool grew into WEV-SMT, an SMT-backed checker, and into two papers about what dependency analyses can and cannot know.

Alongside it I wanted to understand LLM serving from the inside, so I wrote an engine: Mini-vLLM. Then I built CARL, a controller meant to tune it online, and spent longer auditing CARL than building it. Several of my early numbers did not survive that audit. The paper that came out of it reports what did.

  • Measure first

    Numbers here say where they came from: a log, a results file, a manuscript, or my own report.

  • State the scope

    One GPU, one model and two knobs is exactly that, and I say so.

  • Make it recoverable

    Checkpoints, hashes and regression tests for the boring parts.

02Selected work

Two research systems, and the rest

The first two are where most of my time went this year. Each case study has interactive figures, the measured results, and the parts that did not work.

03Research

Papers in review, and how they got there

Nothing below is accepted or published yet, and the labels say so. Each manuscript has its code public, and each states its scope: one model and one GPU for CARL, straight-line 32-bit code for the dependency theorems.

  1. Under reviewMLSys 2027 · Oct 2026

    CARL: Comparing an Online Contextual-Bandit Reconfiguration System with Offline-Tuned Static Configurations of an LLM Serving Engine

    V. Vijayakumar Suja

    A paired comparison over ten seeds on a Tesla T4. At a saturated burst point the controller beat a non-learning rule by 3.76 tok/s but stayed below static configurations chosen offline for the same objective. At a sub-critical Poisson load it trailed both on end-of-run utility, and no run met the convergence diagnostic.

  2. Under reviewTACAS 2027, submission #4549 · Oct 2026

    The Limits of Instruction-Local Dependency Summaries, with an Application to Thin-Air Reads

    V. Vijayakumar Suja, M. Doko

    Proves in Isabelle/HOL that no Boolean depends-or-not summary restricted to an instruction's read registers stays exact under composition, and that composed expression labels do. With an exact per-instruction SMT oracle, the prototype's closure catches all 66 single-instruction fake dependencies but none of the 72 written as chains, while keeping all 171 real ones.

  3. Under reviewFSEN 2027, submission 41 · Nov 2026

    The Limits of Read-Restricted Dependency Summaries

    V. Vijayakumar Suja

    Characterises what an exact instruction-local summary must keep and when Cousot's composition is already exact. The empirical side is negative and reported as such: across 2,250 litmus tests and eight upstream concurrency code bases, no composed cancellation appeared in a store's data dependencies.

  4. DissertationMSc dissertation, Heriot-Watt University · Apr 2026

    Visualising WEAKEST Executions

    V. Vijayakumar Suja, supervised by Dr M. Doko

    Design, implementation and evaluation of an interactive JavaFX tool for exploring executions under the WEAKEST memory model, including a user study with nine participants. Graded Exceptional (78/100).

Research timeline

  1. Oct 2025

    Ethics approval and project proposal

    Proposed an interactive tool for exploring executions of concurrent programs and applied for ethics approval for a user study.

  2. Apr 2026

    Dissertation submitted

    WEAKEST Execution Visualiser, with a five-model comparison view and a nine-person user study.

  3. May 2026

    Mini-vLLM engine work begins in earnest

    Continuous batching, paged KV cache and HF parity tests, then prefix caching, chunked prefill and metrics.

  4. Aug 2026

    WEV-SMT reaches real corpora

    Litmus parser for five architectures, validation over herd7 and Dat3M tests, fence and RMW encoding.

  5. Sep 2026

    CARL audit and repair

    A claim ledger retracted results the repository's own artifacts contradicted. The controller and reward were repaired and re-run on a T4.

  6. Oct 2026

    Two submissions

    TACAS 2027 on dependency summaries, and MLSys 2027 on CARL, each with three-campaign provenance and stated scope.

  7. Nov 2026

    FSEN 2027 submission

    Read-restricted dependency summaries, with a negative result from real code reported alongside the theorems.

04Archive

Everything else, filed properly

Coursework and side projects, described from their source code and reports. The archive has filters by category, technology and type.

05Skills

Skills, each with a receipt

Pick an area, then a skill, to see which projects actually use it.

How a serving engine decides what runs on the GPU next, and how to tell whether a change helped.

Projects behind ai systems and inference

06Problem solving

Mostly mediums, all in Java

A snapshot of my public LeetCode profile, taken on 18 November 2026. LeetCode has no stable public API, so these numbers are cached rather than live.

Solved

153

problems · Java for every one

Easy
33
of 976
Medium
93
of 2,148
Hard
27
of 991
Full profile on LeetCode

Most practised topics

Problems solved per tag. A problem can carry several tags.

  • Array68
  • String37
  • Dynamic Programming33
  • Tree26
  • Hash Table23
  • Two Pointers23
  • Linked List22
  • Depth-First Search20
  • Backtracking19
  • Math19
  • Breadth-First Search13
  • Stack13
07Journey

Where I have been

  1. Until Jul 2023

    Education

    BTech, Computer Science

    College of Engineering Muttathara, Kerala

    Undergraduate computer science: data structures, operating systems, networks and databases.

  2. Dec 2023 to Aug 2024

    Experience

    Research Software Engineer Intern, Retrieval and RAG

    Kompetenzen Technologies, Thiruvananthapuram

    Part of a five-person research team building document intelligence and retrieval systems.

    • Hybrid retrieval with BM25, dense embeddings and cross-encoder reranking. nDCG@10 went from 0.58 to 0.68 on 500 held-out queries.
    • Citation mapping and evidence-based abstention cut unsupported claims from 18% to 9% at 80% answer coverage.
    • Bounded candidate sets, batched reranking and async handling took p95 retrieval latency from 1.2 s to 0.8 s at 20 users.
    • Checkpointed, transactional ingestion with content-hash deduplication: zero duplicate records across 100 injected-failure tests.
    Self-reported· figures from internal evaluation; no public artifact
  3. Awarded Jun 2026

    Education

    MSc Software Engineering

    Heriot-Watt University, Edinburgh

    Machine Learning, Concurrent Systems, Formal Methods, Distributed Computing, Rigorous Methods, Industrial Programming and 3D Graphics. Dissertation graded Exceptional, 78/100.

  4. Jan 2026 to present

    Research

    Independent systems research

    Edinburgh

    Mini-vLLM and CARL on the inference side; WEV-SMT and two dependency-summary papers on the verification side. Three manuscripts under review.

08 Contact

If you work on serving, schedulers or correctness, I would like to hear from you.

I am looking for software engineering roles in AI infrastructure, inference and systems. I am based in Edinburgh with the right to work in the UK (UK Graduate Route visa, valid through October 2028).