Candidate.
Kanvis
?

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

Hiring? Every applicant arrives already interviewed.

Overview

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

2023 – Present

WORK

Research Lead (ML for Chemical Reaction Modeling)

Auxilart (Industry-Academic Collaboration)
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.
•Built Transformer-based encoder for irregular chemical trajectories.
•Developed sparse-autoencoder based domain adaptation module.
•Implemented full ODE-based data-generation pipeline.

Key Achievements

→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

Jul 2022 – Present

WORK

Machine Learning Consultant

Zeta Solutions
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.
•Automated digitization of factory equipment manuals into proprietary formats using LLMs, enabling seamless integration with internal software.
•Automated auditing by leveraging LLMs and VLMs to match invoices and documents with transactions, verify accuracy, and flag discrepancies.
•Built computer vision models for automated text detection in videos, streamlining translation and post-production in the entertainment industry.
•Developed agentic workflows for AI-generated wizards to assist novice lawyers in drafting standard contracts to reduce time spent on boilerplate work.
•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.
•Extracted oil-pump efficiency curves from legacy documents using computer vision and curve fitting, facilitating optimized oil flow routing.

Key Achievements

→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

Sep 2024 – Aug 2025

WORK

Research Assistant

Intelligent Machines & Sociotechnical Systems Lab, LUMS
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.
•Developed a multi-agent no-regret learning framework for financial decision making and regime shifts.
•Implemented large-scale simulation and stress-testing pipeline.

Key Achievements

→Outperformed S&P 500 and gold on risk-adjusted returns.
→Paper accepted at AI4DF Workshop @ ICAIF 2025.
Multi-agent learningNo-regret learningSimulation pipeline

Jun 2024 – Jul 2025

WORK

Research Assistant

Electrical Engineering Department, LUMS
Supervised by Dr. Muhammad Tahir. Self-Supervised Financial Modeling with RL: Developed multiresolution time-series representation model using transformer feature generator and PPO-guided pretext tasks; processed 20+ TB of data with Python-C++ pipelines on Cloud Run, BigQuery, and Cloud Storage. Unsupervised Domain Adaptation with Sparse Autoencoders: Designed SAE-based domain-invariant encoder improving cross-domain and few-shot performance for vision backbones.
•Developed multiresolution time-series representation model using transformer feature generator and PPO-guided pretext tasks.
•Processed 20+ TB of data with Python-C++ pipelines.
•Designed SAE-based domain-invariant encoder for vision backbones.

Key Achievements

→Improved cross-domain and few-shot performance for vision backbones.
→Successfully managed 20+ TB data processing on cloud infrastructure.
PPOTransformersPythonC++Cloud RunBigQueryCloud StorageSparse Autoencoders

Project Portfolio

ACADEMIC

Present

Job Posting Analytics

Lead Designer

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
PERSONAL

Present

Scalable RAG Pipeline for Secure Knowledge Processing

Developer

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

Sep 2021 – Jul 2025

B.S. Computer Science

Lahore University of Management Sciences (LUMS)Specialization in Computer Science
GPA: 3.48

Relevant Coursework

Reinforcement LearningAdvanced Topics in MLMultiagent SystemsRoboticsDistributed SystemsData ScienceMachine LearningDeep learning

Impact & Recognition

Patents & Publications

2025 · PUBLICATION

No-Regret Portfolio Optimization

Accepted, AI4DF Workshop @ ICAIF 2025

Team:Dr. Hassan Jaleel
PUBLICATION

Organic reaction mechanism identification under real-world data heterogeneity

Under Review, ESCAPE 36

Skills & Interests

Python

NumPy

Pandas

Retrieval-Augmented Generation

PyTorch

Large Language Models

Reinforcement Learning

scikit-learn

Hugging Face Transformers

Domain Adaptation

C/C++

SQL

TensorFlow

BigQuery

Cloud Storage

Cloud Run

PostgreSQL

No-Regret Learning

Self-Supervised Representation Learning

Bash/Shell

JavaScript/TypeScript

Redis

Docker

Go

Let's Connect

I'd love to hear from you. Feel free to reach out.

These unlock once you finish onboarding and publish your profile.

More people on Kanvis

Browse more people