jv. Résumé

Optimization & Machine Learning / London, UK

Javal VyasFrom complex systems
to better decisions.

I develop optimization algorithms, machine learning methods, and Python research software for decision-making under constraints. My work spans energy-system modelling, scheduling, and agentic control.

PhD student · Imperial College London

Explore my work View résumé
GitHub LinkedIn Google Scholar
Portrait of Javal Vyas
Research. Build. Validate.
At the intersection ofMachine learningMathematical optimizationResearch engineering

01 / Selected work

Ideas, implemented.

Research systems and open-source tools.
From the underlying model to working code.

Mathematical modelling · Energy 01

Unit Commitment Optimization

Optimization models and decomposition algorithms for meeting electricity demand at minimum cost under combinatorial commitment constraints.

  • Decomposition method paired with EGRET unit commitment models
  • Benchmarked across four power-system cases
Energy SystemsOptimizationScheduling
Read paper
AI systems · Control 02

Fault-Tolerant Control with LLM Agents

Agentic decision framework that turns fault signals into constraint-aware recovery plans, then checks candidate actions through simulation and deterministic validators.

  • Multi-agent monitoring, planning, action synthesis, simulation, and reprompting
  • Evaluates action reliability under process constraints before execution

My contribution Built most of the system, including the agent architecture, simulation, validators, and experiments. Collaborators developed the knowledge graph and SPARQL queries.

LLM AgentsValidationControl
Read paper View code
Multimodal AI · Graphs 03

P&ID to Process Graphs

Multimodal language-model workflow for extracting equipment tags and reconstructing process topology from P&ID drawings.

  • Separates visual extraction from topology reasoning
  • Targets scalable, semantically reliable P&ID digitization
Multimodal MLGraphsStructured Data
Read paper
Open-source software · Optimization 04

rtn_scheduling

Python package for solving resource-task-network scheduling problems with Pyomo, including experiment and visualization utilities.

  • Resource-task-network inputs
  • Gantt, resource-level, and network visualizations
PythonPyomoOptimization
View code

02 / Publications

Research in the open.

Full Google Scholar profile
  1. 2026

    Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models

    arXiv preprint

    ↗
  2. 2026

    From Detection to Action: Using LLM Agents for Fault-Tolerant Control

    arXiv preprint

    ↗
  3. 2026

    From P&ID Drawings to Process Graphs: A Multimodal Language Model Approach

    Systems and Control Transactions journal article

    ↗
  4. 2025

    Optimization models and algorithms for the Unit Commitment problem

    Systems and Control Transactions journal article

    ↗
  5. 2024

    Integration of Plant Scheduling Feasibility with Supply Chain Networks Under Disruptions Using Machine Learning Surrogates

    ESCAPE conference

    ↗

03 / Approach & expertise

Rigorous models.
Useful software.

I work on decision-making under constraints: how to model a complex system, learn from its data, and check whether a proposed action will actually work.

I’m a PhD student in Chemical Engineering at Imperial College London’s Autonomous Industrial Systems Laboratory, with expected completion in December 2027. Previously, I worked as an Engineer II at KeyLogic in Pittsburgh on IDAES and PARETO.

Interested in quantitative research and development, with additional interests in AI/ML research and research engineering.

Explore my background
01

Research Engineering

Python · Git · Linux · Docker · CI/CD

02

Optimization

Optimization · Scheduling · MILP / MINLP · Decomposition · Experiment design

03

ML Systems

Machine learning · Uncertainty diagnostics · Validation loops · Surrogates · Model evaluation

04

Agents / Knowledge

Agentic workflows · Retrieval / Graph RAG · Knowledge graphs · Tool use · Semantic constraints

05

Systems Domain

Process control · Fault handling · Energy systems · Digital twins · P&ID digitization

04 / Background

Research & experience.

Imperial College London

Sep 2024 – Dec 2027 (expected)

PhD student

Chemical Engineering · Autonomous Industrial Systems Laboratory

Research in optimization, machine learning, and autonomous industrial systems.

KeyLogic

Pittsburgh, USA

Engineer II

Worked on the IDAES and PARETO projects.

05 / Get in touch

Let’s solve something
interesting.

For quantitative research and development, AI/ML research, and research engineering opportunities.

javalvyas2000@gmail.com
GitHub LinkedIn Medium Google Scholar