Danish AhmedAI Engineer & Solution Architect

Problem

Existing recruitment and knowledge-reasoning workflows relied on manual processing, simple rule-based logic, and slow AI pipelines, resulting in high latency, low transparency, and limited scalability across enterprise use cases.

Approach

Designed and optimized end-to-end AI pipelines for resume parsing, candidate ranking, and automation using hybrid LLM + OCR architectures. Built modular, agent-based systems for parsing, scoring, ranking, reporting, and outreach. Implemented custom ranking pipelines with transparent justification via FastAPI and Python ETL workflows. Developed advanced RAG and graph-based reasoning engines for large-scale text corpora, combining knowledge graphs, iterative query refinement, and prompt optimization. Automated orchestration and monitoring using n8n and LangSmith.

Impact

Reduced resume parsing latency from 15 seconds to 3 seconds through parallel processing and batching while maintaining high accuracy. Achieved candidate scoring at scale, reduced manual data wrangling by 80%, and delivered AI systems with over 90% retrieval and reasoning accuracy. Enabled enterprise clients to deploy transparent, scalable, and auditable AI-driven workflows across recruitment and knowledge reasoning domains.

Technologies

Problem

An internal application relied on hard-coded rules to analyze structured input data, making it difficult to adapt when data patterns changed.

Approach

Collected and cleaned tabular datasets using Pandas, engineered input features, and trained classification models using Scikit-learn. Implemented a PyTorch prototype to compare results against classical models. Wrapped the selected model inside a FastAPI service with a `/predict` endpoint and tested requests using payloads. Managed code versions and iterations using Git.

Impact

Replaced rule-based logic with a deployable ML inference service, enabling the team to update model behavior through retraining instead of code changes and accelerating experimentation during development.

Technologies

Problem

Students struggled to translate theoretical concepts in Python and machine learning into working code for data analysis and modeling tasks.

Approach

Conducted guided lab sessions covering data preprocessing, data visualization, and implementation of basic machine learning models. Reviewed student code, debugged errors, and provided targeted feedback to improve correctness and clarity.

Impact

Enabled students to independently complete data analysis and machine learning assignments, improving code quality, conceptual understanding, and confidence in working with real datasets.

Technologies

Three-course specialization taught by Andrew Ng covering regression, classification, neural networks, decision trees, recommender systems, and best practices for ML development. Includes hands-on projects implementing algorithms from scratch.

A VS Code extension that analyzes code changes and provides intelligent suggestions for improvements, bug detection, and best practices.

Problem

Code reviews are time-consuming and often miss subtle bugs or style inconsistencies.

Approach

Integrated GPT-4 API with custom prompts for code analysis. Built VS Code extension using TypeScript and implemented caching for performance.

Impact

1,000+ downloads, 4.8/5 star rating, featured in VS Code marketplace. Reduced average code review time by 40% in beta testing.

Technologies

A feature-rich collaborative whiteboard application with drawing tools, shapes, text, and real-time collaboration using WebSockets.

Problem

Existing whiteboard solutions were expensive or lacked real-time collaboration features.

Approach

Built with React for frontend, Node.js + Socket.io for real-time communication, and Canvas API for drawing. Implemented operational transformation for conflict resolution.

Impact

Used by 5,000+ users. Featured on Product Hunt with 200+ upvotes.

Technologies

Cross-platform mobile app that automatically categorizes expenses using machine learning and provides personalized budget recommendations.

Problem

Manual expense tracking is tedious and people often lose track of spending patterns.

Approach

Built with React Native for cross-platform support. Implemented ML model for expense categorization using TensorFlow.js. Used Firebase for backend.

Impact

10,000+ downloads, 4.5/5 rating on app stores. Helped users save an average of $200/month.

Technologies

A comprehensive CLI toolkit that automates infrastructure provisioning, CI/CD setup, and monitoring configuration.

Problem

Setting up DevOps infrastructure for new projects was repetitive and error-prone.

Approach

Built with Python and Click framework. Integrated with AWS, Docker, and Kubernetes APIs. Created templates for common setups.

Impact

500+ GitHub stars. Reduced infrastructure setup time by 80% for new projects.

Technologies