ML Systems Researcher | Scaling RAG to 10M Tokens/Sec | LUMS '25

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

Hire me

Computer Science researcher and ML consultant specializing in efficient ML systems, domain adaptation, and reinforcement learning. Proven track record of scaling high-performance RAG pipelines to 10M tokens/sec and automating complex industrial workflows for global clients like Warner Bros and ExxonMobil. Currently pursuing a BS at LUMS with a focus on high-scale distributed systems and multi-agent learning.

Experience

Research Lead (ML for Chemical Reaction Modeling)

Auxilart (Industry-Academic Collaboration)work2023 – Present

Summary

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.

What I did

  • Developed sparse-autoencoder based domain adaptation module.

Results

  • Achieved 99.8% accuracy (20% masking) and 93.4% (40% masking) in reaction mechanism identification.
  • Research under review for ESCAPE 36.
TransformersSparse-autoencodersODE-based data generation

Machine Learning Consultant

Zeta SolutionsworkJul 2022 – Present

Summary

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 number of man-hours required for auditing by up to 90%.
  • Successfully automated environmental compliance reviews for clients such as ExxonMobil and Dow Chemicals.
LLMsVLMsComputer VisionAgentic WorkflowsCurve Fitting

Research Assistant

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

Summary

Supervised by Dr. Hassan Jaleel. 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

  • Paper accepted at AI4DF Workshop @ ICAIF 2025.
Multi-agent learningNo-regret learningSimulation pipeline

Skills

Technical

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

Projects

Job Posting Analytics

Lead Designeracademic
Supervised by Mobin Javed. 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.
SLMsWeb ScrapingData Pipeline

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.
RAGEmbeddingsServerlessThreading

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

With Dr. Hassan Jaleel

Organic reaction mechanism identification under real-world data heterogeneity

publication

Under Review, ESCAPE 36

Hire themReach out about a role, a contract or a conversation.For recruiters

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

More people on Kanvis

Browse more peopleCreate your own Kanvis