Muhammad Aarash Abro

ML Engineer | Scaling RAG Pipelines & Automating Enterprise Workflows

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

Hire me

Machine Learning Engineer specializing in high-scale AI systems, from processing 20+ TB of financial data to building agentic workflows for global firms like BDO and Warner Bros. Expert in RAG, RL, and time-series modeling with a focus on measurable efficiency gains and research-backed solutions.

Experience

Research Lead (ML for Chemical Reaction Modeling)

Auxilart (Industry-Academic Collaboration)work2023 – Present

Summary

Leading research on organic reaction mechanism identification under real-world data heterogeneity.

What I did

  • 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.

Results

  • Achieved 99.8% accuracy (20% masking) and 93.4% (40% masking) in reaction mechanism identification.
TransformersSparse-autoencodersDomain AdaptationODE-based data-generation

Machine Learning Consultant

Zeta SolutionscontractJul 2022 – Present

Summary

Worked on multiple high-impact AI automation projects across various industries including legal, finance, and entertainment.

What I did

  • ATR SmartProcedures — AI-Driven Factory Documentation: Automated digitization of factory equipment manuals into proprietary formats using LLMs, enabling seamless 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 post-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, facilitating optimized oil flow routing.

Results

  • Reduced turnaround time per-table by 80% for factory documentation digitization.
  • Reduced man-hours required for auditing by up to 90% through LLM/VLM automation.
LLMsVLMsComputer VisionAgentic WorkflowsCurve Fitting

Research Assistant

Intelligent Machines & Sociotechnical Systems Lab, LUMSLahore, PakistanworkSep 2024 – Aug 2025

Summary

Supervised by Dr. Hassan Jaleel. Focused on financial decision making and regime shifts.

What I did

  • No-Regret Portfolio Optimization (Accepted, AI4DF Workshop @ ICAIF 2025): Developed a multi-agent no-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 multi-agent no-regret learning framework.
Multi-agent learningNo-regret learningSimulation pipelineStress-testing

Skills

Technical

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

Projects

Scalable RAG Pipeline for Secure Knowledge Processing

Developerpersonal
Developed a customizable Retrieval-Augmented Generation (RAG) pipeline to process dense embeddings at scale, enabling secure and cost-efficient knowledge retrieval for businesses. Reached embedding throughput of 10 Million Tokens Per Second throughput with $30 compute budget by optimizing inference through maximal threading of I/O bound processes and parallel serverless processing for compute-bound processes.
RAGEmbeddingsThreadingServerless Processing

Job Posting Analytics

Developeracademic
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.
Small Language Models (SLMs)Web ScrapingData Pipeline

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 at AI4DF Workshop @ ICAIF 2025.

With Dr. Hassan Jaleel

Organic reaction mechanism identification under real-world data heterogeneity

publication

Under Review, ESCAPE 36.

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