Muhammad Aarash Abro

Research Engineer | AI Infrastructure | High-Throughput RAG & Distributed Systems

Currently: Research Lead (ML for Chemical Reaction Modeling), Auxilart (Industry-Academic Collaboration)Experience: 4 years

Hire me

Research Engineer with a track record of bridging the gap between complex algorithmic theory and massive-scale production. Specialized in high-throughput RAG pipelines (10M tokens/sec), multi-agent regret learning for finance, and efficient vision backbones. Thrives in high-pressure, fast-paced environments where technical complexity meets real-world scale. Experience spans from publishing at ICAIF to consulting for global giants like ExxonMobil and Warner Bros. Discovery.

Experience

Research Lead (ML for Chemical Reaction Modeling)

Auxilart (Industry-Academic Collaboration)work2023 – Present
Key Responsibilities: • Organic reaction mechanism identification under real-world data heterogeneity (Under Review, ESCAPE 36): Built Transformer-based encoder for irregular chemical trajectories and sparse-autoencoder based domain adaptation module; achieved 99.8% accuracy (20% masking) and 93.4% (40% masking); implemented full ODE-based data-generation pipeline. Achievements: • Achieved 99.8% accuracy (20% masking) and 93.4% (40% masking) in organic reaction mechanism identification.
TransformerSparse-autoencoderDomain adaptationODE-based data-generation

Machine Learning Consultant

Zeta SolutionsworkJul 2022 – Present
Key Responsibilities: • ATR SmartProcedures — AI-Driven Factory Documentation: Automated digitization of factory equipment manuals into proprietary formats using LLMs, enabling less integration with internal software, reducing turnaround time per-table by 80%. • UHY Prime HK — Audit Automation: Automated auditing by leveraging LLMs and VLMs to match invoices and documents with transactions, verify accuracy, and flag discrepancies, reducing number of man-hours required by up to 90%. • Warner Bros. Discovery — Post Production Video Assistant Automation: Built computer vision models for automated text detection in videos, streamlining translation and production in the entertainment industry. • Whichdraft — AI Legal Assistant for Contract Generation: Developed agentic workflows for AI-generated wizards to assist novice lawyers in drafting standard contracts to reduce time spent on boilerplate work. • Enviro AI — Environmental Compliance Chatbot: Built an agentic reasoning system using TCEQ knowledge bases to automate environmental compliance reviews and permit applications for clients such as ExxonMobil and Dow Chemicals. • BDO Global — Efficiency Modeling and Routing Optimization: Extracted oil-pump efficiency curves from legacy documents using computer vision and curve fitting, tating optimized oil flow routing. Achievements: • Reduced turnaround time per-table by 80% for factory documentation. • Reduced number of man-hours required for auditing by up to 90%. • Streamlined translation and production for Warner Bros. Discovery. • Automated environmental compliance reviews for clients like ExxonMobil and Dow Chemicals.
LLMsVLMsComputer VisionAgentic workflowsTCEQ knowledge basesCurve fitting

Research Assistant

Intelligent Machines & Sociotechnical Systems Lab, LUMSworkSep 2024 – Aug 2025

Summary

Supervised by Dr. Hassan Jaleel

What I did

  • No-Regret Portfolio Optimization (Accepted, AI4DF Workshop @ ICAIF 2025): Developed a multi-agent regret learning framework for financial decision making and regime shifts; outperformed S&P 500 and gold on risk-adjusted returns; implemented large-scale simulation and stress-testing pipeline.

Results

  • Outperformed S&P 500 and gold on risk-adjusted returns using a greedy variant of the no-regret approach.
  • Discovered that hindsight-based investing in constrained search spaces significantly outperforms industry benchmarks.
Multi-agent regret learningSimulation pipelineStress-testing

Skills

Technical

PythonPython
Hugging Face Transformers
NumPy
Pandas
Retrieval-Augmented Generation
Large Language Models
scikit-learn
PyTorchPyTorch
Large-Scale Time-Series
C/C++C/C++
SQLSQL
TensorFlowTensorFlow
BigQuery
Cloud Storage
Cloud Run
PostgreSQLPostgreSQL
Online and Reinforcement Learning
No-Regret Learning
Self-Supervised Representation Learning
Domain Adaptation
DockerDocker
RedisRedis
Bash/ShellBash/Shell
JavaScript/TypeScriptJavaScript/TypeScript
GoGo

Projects

Job Posting Analytics

Developerpersonal
Designed a data pipeline to scrape job postings and extract key skill requirements using Small Language Models (SLMs). Built a job board to aggregate frequently demanded skills by position, simplifying career progression and skill acquisition pathways.
Gemma 2 1BIndeed API/ScrapingData pipelineWeb scrapingSLMs

Distributed Fault-Tolerant State Machine (Raft)

Lead Developeracademic
Implemented the Raft consensus algorithm from scratch to manage a replicated state machine, ensuring fault tolerance and consistency across a distributed cluster. Used Redis for state persistence and Go's concurrency primitives for managing cluster communication and leader election.
GoRedisDistributed SystemsRaft Consensus

Scalable RAG Pipeline for Secure Knowledge Processing

Developerpersonal
Built a high-throughput, enterprise-grade RAG pipeline designed to embed massive data repositories in hours rather than months. Optimized for cost-efficiency, achieving 10M tokens/sec throughput on a $30 budget by leveraging maximal threading for I/O and parallel serverless processing for compute-bound tasks.
RAGEmbeddingsThreadingServerless processing

Education

B.S. Computer Science

Lahore University of Management Sciences (LUMS)Computer ScienceGPA 3.48Sep 2021 – Jul 2025

Coursework

Reinforcement LearningAdvanced Topics in MLMultiagent SystemsRoboticsDistributed SystemsData ScienceMachine LearningDeep Learning

Recognition

Patents & publications

No-Regret Portfolio Optimization

publication2025

Accepted, AI4DF Workshop @ ICAIF 2025

No-Regret Portfolio Optimization (AI4DF Workshop @ ICAIF 2025)

research paper2025
Read it

Organic reaction mechanism identification under real-world data heterogeneity

publication

Under Review, ESCAPE 36

No-Regret Portfolio Optimization (AI4DF Workshop @ ICAIF 2025)

research paper

Developed a multi-agent regret learning framework for financial decision making and regime shifts; outperformed S&P 500 and gold on risk-adjusted returns; implemented large-scale simulation and stress-testing pipeline.

Organic reaction mechanism identification under real-world data heterogeneity (ESCAPE 36)

research paper

Built Transformer-based encoder for irregular chemical trajectories and sparse-autoencoder based domain adaptation module; achieved 99.8% accuracy (20% masking) and 93.4% (40% masking); implemented full ODE-based data-generation pipeline.

Organic reaction mechanism identification under real-world data heterogeneity (ESCAPE 36 / PSE)

research paper

Built Transformer-based encoder for irregular chemical trajectories and sparse-autoencoder based domain adaptation module; achieved 99.8% accuracy (20% masking) and 93.4% (40% masking).

No-Regret Portfolio Optimization (AI4DF Workshop @ ICAIF 2025)

research paper

Developed a multi-agent regret learning framework for financial decision making and regime shifts. Outperformed S&P 500 and gold on risk-adjusted returns using a greedy variant of the no-regret approach.

Read it

No-Regret Portfolio Optimization (AI4DF Workshop @ ICAIF 2025)

publication
Read it

What drives the work

Motivations

  • Solving highly challenging and stimulating problems
  • High-pressure environments
  • Fast-paced innovation

Principles

  • Performance under pressure
  • Algorithmic efficiency
  • Practical R&D
  • High-throughput engineering
Hire MuhammadReach out about a role, a contract or a conversation.For recruiters

Muhammad's twin is AI, it can make mistakes.

More people on Kanvis

Browse more peopleCreate your own Kanvis