Professional Summary
Full-stack software engineer specializing in reliable AI-powered search, retrieval-augmented generation (RAG), enterprise knowledge management, and data integration. Designs and delivers production systems spanning secure conversational AI, multilingual hybrid-search pipelines, recommendation engines, and scalable data infrastructure. Combines software engineering, data science, and applied machine learning to help organizations retrieve trusted information, connect fragmented data, and make complex knowledge more accessible and actionable.
Proposed Endeavor
Advance reliable, secure, and scalable AI-powered knowledge retrieval and enterprise data integration systems in the United States. This work will focus on production-grade RAG applications, multilingual and hybrid search, recommendation systems, and intelligent automation that enable industrial and business platforms to connect fragmented data, improve access to trusted information, and support more efficient decision-making.
Core Expertise
AI & Knowledge Systems: Retrieval-augmented generation, conversational AI, agentic workflows, semantic retrieval, reranking, knowledge-base synchronization, and AI safety guardrails
Enterprise Search & Data Integration: Multilingual indexing, hybrid search, query routing and expansion, Elasticsearch, Solr, Weaviate, MuleSoft, and heterogeneous data-source integration
Scalable Software Systems: Full-stack architecture, distributed caching, load balancing, API development, offline data pipelines, cloud infrastructure, monitoring, and performance optimization
Applied Machine Learning: Natural language processing, recommendation systems, text classification, user behavior analysis, experimentation, and feedback-driven quality improvement
Selected Technical Contributions
Secure Enterprise RAG
Production Conversational AI
Built reliable knowledge-retrieval capabilities for an enterprise digital platform.
- Led end-to-end development of a production RAG conversational application using Azure OpenAI, Redis, and Weaviate, with sticky-session routing and load balancing supporting 1K+ daily active users
- Implemented multi-turn memory, function-calling workflows, input sanitization, content filtering, and PII masking to improve the usefulness, safety, and reliability of AI interactions
Multilingual Knowledge Retrieval
Search and Indexing Infrastructure
Improved access to distributed enterprise knowledge across heterogeneous sources.
- Engineered scheduled multilingual indexing pipelines across 10+ data sources
- Combined keyword and semantic retrieval with reranking, query routing, query expansion, iterative retrieval, caching, and feedback loops to improve relevance and responsiveness
Enterprise Data Interoperability
API Integration and Search
Connected fragmented partner and location data to searchable enterprise applications.
- Designed 7+ MuleSoft integration workflows for incremental data synchronization
- Integrated multi-source records into Solr- and Elasticsearch-based retrieval systems with cache optimization
Intelligent Personalization
Recommendation and ML Pipelines
Applied recommendation methods and behavioral data to improve digital experiences.
- Developed user-to-item and item-to-item recommendation pipelines with rolling caches and CDN integration
- Built offline machine learning pipelines supporting sales-funnel optimization and marketing targeting
Professional Experience
PiSrc
Full-Stack Software Engineer
February 2022 - Present
Lead the development of production AI, enterprise search, data integration, and personalization capabilities for industrial digital platforms.
- AI Chatbot & RAG Systems:
- Led full-cycle development of a production-grade RAG conversational AI chatbot using Azure OpenAI, Redis, and Weaviate vector database; architected sticky session routing and load balancing to support 1K+ DAUs
- Designed multi-turn conversational memory with Redis persistence and context window management; built agentic workflows with function calling to orchestrate custom tools and external APIs
- Implemented security guardrails including input sanitization, content filtering, and PII masking to ensure safe and compliant AI interactions
- Delivered real-time AI Overview and autosuggest powered by live user queries with caching layer for low-latency responses; built scheduled report pipelines and user feedback loops to continuously improve relevance and quality
- Engineered scheduled multilingual (I18N) indexing pipelines across 10+ heterogeneous data sources, combining keyword-based and semantic hybrid search with semantic reranking, multi-channel query routing, query expansion, and iterative retrieval
- Infrastructure & Platform Engineering:
- Architected scalable full-stack infrastructure: VM provisioning, runtime orchestration, and offline pipelines for knowledge base synchronization and cache optimization
- Maintained high reliability and low-latency performance through proactive monitoring and tuning
- Applied data-driven insights to evolve CMS architecture and scale web platforms
- Data Integration & Search Optimization:
- Designed 7+ MuleSoft API integration workflows for incremental delta updates of partner accounts and locations
- Integrated multi-source data into a Solr and Elasticsearch–based search layer with cache optimization
- Personalization & Machine Learning Pipelines:
- Developed User-to-Item and Item-to-Item recommendation pipelines with rolling cache and Akamai CDN integration
- Built offline ML pipelines to optimize sales funnel conversion and marketing campaign targeting
- Content Platform (AEM):
- Developed licensable software modules on Adobe Experience Manager to streamline content authoring and multi-channel publishing
Stevens Institute of Technology
Research Assistant/Teaching Assistant, Deep Learning and Web Analytics
June 2020 - December 2021
Language features pattern detection with Deep Learning models, data parsing and statistics modeling
- Cleaned and structured 94,581 earnings call transcripts to explore 96 language factors influencing stock return
- Achieved 72% accuracy on text classification with a domain-adapted BERT language model using PyTorch
- Conducted text analysis, sentiment analysis, and text mining utilizing NLP techniques with SpaCy and NLTK
- Set up and managed a remote GPU environment on Ubuntu for Machine Learning and Deep Learning tasks
- Developed tutorials on implementing deep learning models using related Python packages
Education
Monroe University
Master of Business Administration (MBA), In Progress
2025 - Present
Selected Coursework: Strategic Marketing & Data Mining, Software System Design, Computer Networks, Research & Statistics for Managerial Decision-Making, Organizational Behavior & Leadership in the 21st Century, Managing in the Global Environment
Stevens Institute of Technology
MSc in Data Science (GPA 3.8/4.0)
September 2019 - December 2021
Relevant Coursework: Statistical Methods, Statistical Inference, Advanced Optimization Methods, Advanced Data Analytics & Machine Learning, Deep Learning, Natural Language Processing, Web Analytics, Database Management Systems, Web Programming, Data Structures & Algorithms
Guangzhou University
BSc in Mathematics and Applied Mathematics
September 2014 - May 2018
Relevant Coursework: Probability and Mathematical Statistics, Operational Research, Numerical Analysis, Advanced Algebra, Mathematical Analysis, Real Function Theory, Functional analysis, Ordinary Differential Equations, Partial Differential Equations
Awards & Honors
Provost's Scholarship
Stevens Institute of Technology
2019
Awarded the Provost’s Scholarship during the MSc in Data Science program.
National Mathematical Modeling Contest
Second Prize
2015
Ranked in the top 6.3% out of 25,558 teams.