AI Engineer with 1+ years in ML backends & Generative AI.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI Software Engineer specializing in scalable ML backends and Generative AI. With deep expertise in engineering local-first RAG architectures, I help enterprises deploy production-ready LLMs while maintaining absolute data privacy and optimizing hardware constraints. My focus bridges rigorous data science methodologies with robust backend orchestration to build context-aware workflows that solve practical business challenges.
Szabist Islamabad
Masters of Data Science
August 1, 2025 – Present
Iqra University Karachi
Bachelors of Computer Science
N/A – June 30, 2024
Cognetex
Ai Engineer
March 1, 2025 – Present
India
Aptech
Data Analyst
June 1, 2024 – December 1, 2024
India
ContexAI - RAG based Monitoring System
June 24, 2026 – Present
Engineered an enterprise document intelligence platform capable of parsing PDFs, Excel files, and archives, automating the ingestion and embedding process for 50+ documents. Implemented a hybrid chunking strategy (semantic, overlapping, and sliding window), optimizing context preservation and increasing vector retrieval accuracy by 20%. Built local vector search pipelines utilizing ChromaDB and BGE embeddings with custom reranking mechanisms, boosting query precision by 25%. Developed semantic search and structured extraction tools, accelerating enterprise knowledge discovery and reducing manual document review time by 43%.
Enterprise RAG-Ops Platform – Knowledge Assistant
June 24, 2026 – Present
Architected a local-first RAG platform on Kubernetes (K3d) utilizing Ollama and ChromaDB, enabling secure internal knowledge retrieval for 3 concurrent users with sub-800ms latency. Engineered a FastAPI gateway and automated data pipeline for file ingestion, processing 8 documents while delivering real-time context-aware streaming. Deployed MinIO and PostgreSQL for secure object storage and structured logging, managing 3.4 GBs of raw data and achieving 100% auditability of all LLM interactions. Integrated Grafana to monitor vector counts and RAG generation latency, reducing system debugging time by 40%. Automated CI/CD workflows via GitHub Actions for Docker builds and Kubernetes updates, decreasing deployment times from hours to minutes
NLP-Focused Resume Analyzer
June 24, 2026 – Present
Engineered an NLP-driven resume analysis pipeline utilizing TF-IDF keyword weighting and similarity matching, automating candidate scoring and reducing manual screening time by 60%. Implemented custom Named Entity Recognition (NER) models to extract 1200+ specific technical skills, generating data-driven candidate evaluations that improved matching accuracy by 30%. Prototyped and validated the end-to-end system via a Streamlit interface, processing a test dataset of 895 resumes and achieving a parsing accuracy of 93%.
Cultural Fit Analysis
The candidate's projects demonstrate a strong alignment with the target role of an AI Engineer, particularly in the Generative AI and MLOps space. The diversity of projects, from RAG systems to NLP-driven analyzers, shows a broad interest and capability within AI. The experience with Kubernetes, Docker, and CI/CD indicates a readiness for modern development and deployment practices. The volunteer work and hackathon participation suggest a proactive and engaged individual, which generally contributes positively to cultural fit.
Soft Skills & Operational Fit
The candidate's project descriptions highlight a results-oriented approach, focusing on quantifiable improvements (e.g., 'reducing manual review time by 43%', 'boosting query precision by 25%'). The experience in training end-users suggests good communication and a collaborative mindset. The automation of CI/CD workflows indicates a proactive approach to operational efficiency. However, without direct assessment data, these are inferred from project descriptions.