Product engineering
React, Next.js, Vue, Node.js, Express, FastAPI, REST, WebSocket
Bingxi Jiang · Software Engineer
I build systems that make AI useful.
Production software, agent workflows, real-time infrastructure, and applied machine learning.
Irvine, California · Available for thoughtful engineering work
Engineering profile
Software first. Applied AI when it earns its place.
I build the product and infrastructure around intelligent systems: interfaces, APIs, queues, data contracts, evaluation loops, and observability.
Systems and data
PostgreSQL, MySQL, MongoDB, Redis, Kafka, Elasticsearch, ETL
Cloud and reliability
AWS, GCP, Docker, Kubernetes, CI/CD, Nginx, Sentry, observability
Applied AI
PyTorch, evaluation, RAG, LoRA, multimodal systems, model serving
TypeScriptPythonReactNode.jsPlaywrightFastAPIPostgreSQLRedisDockerKubernetesPyTorchLLM evaluationTypeScriptPythonReactNode.jsPlaywrightFastAPIPostgreSQLRedisDockerKubernetesPyTorchLLM evaluation
Selected work
Software with a point of view.
Real-time multimodal transcription and memory
Noted
Streams 16kHz PCM audio to Deepgram with sub-300ms latency, combines diarized transcripts with Gemini Vision context, and retrieves memories across sessions with RAG.
Node.jsWebSocketDeepgramGemini
View source 
AI task breakdown and live focus telemetry
FocusTrail
A Gemini-powered task orchestration system with a React interface, Server-Sent Events, a macOS focus agent, and a GCP deployment path.
ReactExpressGeminiGCP
View source 
Schema-driven academic ETL
Course Helper
Converts heterogeneous syllabi into validated, calendar-ready JSON and serves more than one thousand uploads daily with PostgreSQL and Redis.
ETLPostgreSQLRedisAWS
Live product 
Domain LLM evaluation suite
LongevityLLM Benchmark
A seven-task evaluation suite with ontology-grounded scoring for genes, alleles, MP IDs, lifespan direction, sex effects, and longevity-pathway reasoning.
PythonEvaluationBioinformaticsLLMs
View source 
Recognition
1st placeStreamlit AI Hack
Built and demonstrated an AI application with Snowflake Cortex under a short product deadline, earning first place at PyCon US 2026.
Experience
Software engineering across product, platform, and production AI.
The homepage prioritizes engineering roles. Research experience remains available in the complete archive.
Full experience archiveCompany logos
Jun 2026 - Present
AI Quality Engineer Intern
Dassault Systèmes
San Diego, CA
Building software and agent infrastructure that turns legacy enterprise quality workflows into reliable, inspectable Playwright systems.
- Architected a modular Playwright and TypeScript framework with reusable API, session, nested-frame, AG Grid, and reporting layers.
- Integrated Playwright and 3DEXPERIENCE MCP servers for live UI inspection, selector synthesis, and iterative failure repair.
- Cut a 23-step workflow from 40-50+ minutes to 3-4 minutes while expanding validation checkpoints from 6 to 23.
TypeScriptPlaywrightAgent systemsQuality engineering
Apr 2026 - Jun 2026
Software Engineer Intern
GTechFin Inc
New York, NY
Designed an end-to-end workflow engine for trend mining, scripting, asset generation, and AI video production.
- Architected a Python and Typer workflow engine plus MCP service with rerunnable DAG stages, parallel branches, and persisted handoffs.
- Modeled pipeline state in MySQL with normalized tables, transactions, indexes, foreign keys, and idempotent retries.
- Benchmarked MongoDB and Elasticsearch, then built a self-hosted cosine index for 500-5K videos with incremental updates.
PythonMCPMySQLWorkflow engines
Sep 2025 - Dec 2025
Software Engineer Intern
Fresh Road Inc
San Jose, CA
Built the real-time backend and operations layer for a multi-tenant AI voice product deployed across thirteen B2B clients.
- Streamed Twilio audio to Deepgram, language models, and CRM services over WebSockets in a Node.js and Express backend.
- Orchestrated six BullMQ and Redis queues with retries, backoff, delayed jobs, deduplication, and failed-job recovery.
- Cut LLM cost 32% and p95 latency 18% while tracing HTTP, WebSocket, queue, model, and CRM paths with correlation IDs and Sentry.
Node.jsWebSocketRedisObservability
Jun 2025 - Sep 2025
Computer Vision Algorithm Engineer Intern
Ping An Technology
Guangdong, China
Engineered the data, model, serving, and deployment path for vehicle-damage understanding at production scale.
- Built a six-stage Python pipeline for multi-view ingestion, quality checks, localization, classification, scoring, and reports.
- Curated a 2.27M-image training set and fine-tuned Qwen2.5-VL with LoRA, lifting recall 10% and precision 6%.
- Optimized INT8 serving with dynamic batching, cutting p95 latency 38% and raising throughput 50% for services handling 10K+ daily requests.
PythonComputer visionModel servingKubernetes
Events attended
Rooms I was part of.
A visual record of conferences, private sessions, and hackathons.
Education and perspective
Engineering is a people problem with technical consequences.
I am a software engineer and machine learning researcher who enjoys bridging complex model capabilities with practical user-facing systems. Outside the build, I spend time on badminton, hiking, frisbee, content creation, and video editing.
I care about helping other builders move forward, whether that means organizing a technical event, judging a hackathon, sharing research guidance, or debugging the seam between two parts of a system.
University of California, Irvine
B.S. Computer Science + Business Information Management
Expected December 2027GPA 3.822 / 4.0
Artificial Intelligence, Machine Learning, Information Retrieval, Probability and Statistics, Database Management