# Jianxiang Gao > AI Software Engineer , Building Scalable AI Systems Location: Mountain View, California, United States Profile: https://flows.cv/jianxiang I’m an experienced Full-Stack AI Software Engineer with a proven track record of building scalable applications and reliable AI agent systems end to end. I thrive in fast-paced startup environments, take high ownership of my work, and consistently deliver production-grade systems that scale. With deep experience in AI agent architecture, voice AI infrastructure, and real-time interaction systems, I’ve built and deployed applications — sometimes solo — serving thousands of active users. My toolset spans LiveKit, LangChain, Ray Serve, and other modern AI frameworks that enable seamless orchestration between LLMs, APIs, and real-world workflows. I’m fluent in leveraging AI tools to 10× development speed while maintaining high reliability and engineering quality. Passionate about innovation, I stay constantly up to date with the latest advancements in LLMs, RAG systems, and agentic workflows, exploring new ways to turn cutting-edge research into usable products. I believe every engineer should embrace a product-manager mindset—especially in the AI era, where engineers often drive the most critical product decisions. I’ve adopted this philosophy throughout my career, always thinking beyond code to understand user needs, product strategy, and long-term impact. If you’re building the next generation of AI-powered products and value speed, precision, and ownership, I’d love to connect and collaborate. ## Work Experience ### Senior AI Software Engineer @ Brellium Jan 2025 – Present ### AI Software Engineer @ Brellium Jan 2025 – Jan 2025 | New York, United States - Proactively identified bottlenecks in internal engineering workflows, then proposed, developed, and deployed end-to-end solutions that improved team efficiency and development velocity. - Built a generalized file processing system leveraging vLLM, capable of extracting structured data from highly unstructured clinical documents with 99.99%+ accuracy, using a flexible marker-file schema. - Designed an innovative marker-based learning framework to drastically reduce parsing cost and latency while improving extraction accuracy, setting new internal standards for document understanding. - Developed an internal agentic coding assistant that automated repetitive workflows, saving over 80% of engineering time and significantly accelerating customer onboarding. ### Founder & CEO @ LiveQ Jan 2024 – Present - Built LiveQ, an AI-powered desktop assistant that helps users in real time through voice-based interaction and context-aware intelligence. - Designed a multimodal agent framework capable of interpreting on-screen context, user intent, and personalized workflows to deliver seamless, adaptive assistance. - Developed the web console using Next.js and the main application using Electron, integrating both into a cohesive user experience. - Leveraged LiveKit as the core voice infrastructure, and developed a custom in-house AI agent system optimized for latency, reliability, and dynamic task routing. - Personally conducted 50+ client interviews within the first month to gather feedback, validate use cases, and accelerate the development cycle through rapid iteration. ### Software Engineer @ Stonk Tech Inc. Jan 2022 – Jan 2024 | Seattle, Washington, United States - Built complete video media processing pipelines from scratch. - Utilized AWS s3, AWS Textract, AWS CloudFront, AWS LightSail, and MySQL database to construct complete video processing and evaluation pipelines. - Used OOP and Multi-threading to improve the performance of data pipelines. - Individually developed a video ranking system that displays the most appropriate content to the end users. - Individually Constructed an administration panel web application using ant Design Pro, Typescript, and Flask to manage all application users' data. ### Research Software Engineer @ Penn State Natural Language Processing Lab Jan 2023 – Jan 2023 | United States - Developed a conversational agent powered by a Large Language Model (LLM) to assist customers in completing tasks requiring multiple steps and decisions while incorporate multimodal (voice and vision) customer experiences. Try it! Say "Alexa, lets work together" - The application was developed using Amazon's ASK API and deployed on Amazon's EC2 instances for echo devices serving a user base of >50 million, I designed the agents backend using a microservice architecture. Implementing containerization (GPU Docker), caching, load balancing(ECS) for efficient performance and auto-scaling. - Designed and implemented a hybrid system to align LLM-based responses with AWS safety standards, reducing conversation friction and enhancing user response rates by 30%. - Analysed log data to identify & fix bugs with backend services, communicated findings to engineers at Amazon ### NLP Engineer Intern @ Penn State Nittany AI Alliance Jan 2021 – Jan 2023 | United States Worked on SmartOCR project, a tool that automatically scans high school students' transcripts, and extracts useful information like course, grade, and credit information for later application processing. - Built information extraction pipelines from scratch based on desired output and available information. - Achieved over 95% accuracy for the course, grade, and credit information. - Utilized the Agile mode of the development process, having bi-weekly meetings with stakeholders. - Implemented high school transcript recognition with AWS Textract, AWS s3, and NER using Spacy models. ### Machine Learning Engineer, System Architect @ RetroFlux Jan 2022 – Jan 2022 | United States RetroFlux is a portable, instant, content review mobile application that promote long-term knowledge memorization and habit cultivation. - Applied AI models for document content understanding, achieved over 70% accuracy through user testing. - Designed backend architecture and firebase structure individually from scratch. - Adopted Agile mode of development with other team members and real users. - Utilized Firestore and Firebase Storage to construct application's data pipelines and management. ### NLP Engineer Intern, Product Development @ Johnson & Johnson Jan 2021 – Jan 2021 | Remote - Delivered accurate oral and written technical reports of weekly engineering activities. - Utilized AWS and GCP services and Tesseract API into existing OCR workflows, improved accuracy performance by 10%. - Performed field engineering tests on algorithm performance and existing assets, sharing results with supervisors and team members. - Actively Interacted with other team members while working on projects, and frequently communicated with colleagues from different educational backgrounds. ### Founder @ Briefly Jan 2021 – Jan 2021 | United States Briefly is a knowledge management platform that was built to assist better student learning outcomes during the remote learning period. Users can upload media sources like video and audio for automatic bullet points extraction, pop quiz generation, and question answering bot. - Delegated tasks, duties, and responsibilities to 7 team members. - Held weekly meetings to discuss project goals and objectives with other team members. - Applied React with Redux for frontend development and implemented Django backend framework with Celery for asynchronous requests. - Utilized transformer-based NLP models, such as BERT, t5, XLNet, and GPT3, to implement features like text summarization, quiz generation, and chatbots. - Implemented AWS transcribe and s3 services as a part of software implementation. ### Research Assistant @ Penn State University Jan 2020 – Jan 2021 | United States Worked on research project that introduces human-in-the-loop method on semantic parsing models like LDA and NMF. - Reviewed literature to remain current and apply learnings to related research. - Worked on Natural language processing and human-computer interaction. - Built application interfaces with data visualization and text processing using JQuery and HTML to help users interpret texts' topics, and built backend in Django framework. ## Education ### Master of Science - MS in Computer Science (Artificial Intelligence) University of Southern California Jan 2023 – Jan 2025 ### Bachelor's degree in Computer Science Schreyer Honors College at Penn State Jan 2019 – Jan 2023 ### Undergraduate in General Mathematics Penn State University Jan 2019 – Jan 2023 ### High School Diploma Mountain View High School Jan 2016 – Jan 2019 ### part time student in Mathematics Foothill College Jan 2018 – Jan 2019 ### Cyber Security De Anza College Jan 2017 – Jan 2017 ## Contact & Social - LinkedIn: https://linkedin.com/in/jianxianggao --- Source: https://flows.cv/jianxiang JSON Resume: https://flows.cv/jianxiang/resume.json Last updated: 2026-03-20