Mustafa Abbas

Developed and maintained an AI-enabled compliance platform, owning features across the AI, backend, and frontend stack from design through deployment. Integrated AI agents into the platform to automate data extraction and document interpretation, reducing manual data entry and accelerating compliance workflows. Developed across a microservices architecture spanning Node.js/Express and Java/Spring Boot backend services, with a React-based frontend.

Software Engineer – AI/ML & Full-Stack at GoCompliance Team — GoSaaS (2025-06 – 2026-09)

• Developed and maintained an AI-enabled compliance platform, owning features across the AI, backend, and frontend stack from design through deployment.
• Integrated AI agents into the platform to automate data extraction and document interpretation, reducing manual data entry and accelerating compliance workflows.
• Developed across a microservices architecture spanning Node.js/Express and Java/Spring Boot backend services, with a React-based frontend.
• Advocated for and drove team-wide adoption of AI-assisted development tools (Cursor, Claude Code, Codex) and the AWS AI-DLC methodology, standardizing workflows that improved development velocity, code quality, and consistency across the team.
• Collaborated with cross-functional teams to design, implement, and deploy features with a focus on scalability, security, and engineering best practices.

Multi-Agent Path Finding with LLMs (2024-09 – 2025-05)

• Designed a novel multi-agent pathfinding framework for warehouse environments using a fine-tuned GPT-3.5 controller.
• Implemented a feedback loop to parse predicted paths, detect errors, and issue corrective prompts, improving path accuracy and ensuring collision-free navigation.
• Fine-tuned on datasets derived from BFS (single-agent) and CBS (multi-agent) to adapt to varying warehouse layouts.

Second Author, COLING 2025 (2024-06 – 2024-12)

WER We Stand: Benchmarking Urdu ASR Models

• Benchmarked 9 state-of-the-art Urdu ASR models (Whisper, MMS, Seamless-M4T) on read and conversational datasets using WER; conducted error analysis and performance profiling.
• Created the first conversational Urdu ASR dataset (471 Zoom recordings), capturing multi-speaker impromptu dialogue for realistic benchmarking.
• Released fine-tuned models, datasets, and evaluation scripts as open-source resources to accelerate Urdu ASR research.

Research Intern at CSaLT Lab (2023-01 – 2024-05)

Urdu NLP Tooling and Dataset Development

• Enhanced NLTK for Urdu by implementing POS tagging, NER, and text summarization capabilities; evaluated LLMs (GPT, LLaMA) against existing methods for POS tagging.
• Created the Wiki-UQA dataset (200+ Urdu Wikipedia QA pairs) using a semi-automated annotation pipeline with spaCy, Pandas, and manual linguistic review.

Teaching Assistant – CS-370: Operating Systems at Lahore University of Management Sciences (2024-09 – 2025-01)

• Assisted in a core course with 220 students across two sections, and conducted office hours twice a week to support students with course material and assignments.
• Designed, tested, and guided students through complex programming assignments, delivering assignment-based tutorials to reinforce key concepts.
• Graded exams and assignments, ensuring timely feedback and academic support.

Teaching Assistant – CS331: Introduction to Artificial Intelligence at Lahore University of Management Sciences (2024-01 – 2024-05)

• Supported a class of 120 students, holding weekly office hours to address queries and provide course assistance.
• Developed and delivered assignments aligned with key AI concepts, fostering an engaging learning experience.
• Conducted tutorials that deepened understanding of AI content while grading quizzes and assignments to offer constructive feedback.

BS in Computer Science – Lahore University of Management Sciences (2021-09 – 2025-06)