Looking for a job

Jisheng Jiang

@jishengjiang

Message

Software engineer at The Paddock who shipped motorcycle support and cut follower data payloads by 99.7%.

United States

Message

What I'm looking for

I’m looking for new-grad software engineering opportunities in backend or distributed systems, infrastructure, full-stack engineering, or ML/AI infrastructure.

At The Paddock, I expanded the product from cars to motorcycles while preserving existing automotive features. I also reworked social graph pagination and exact-count queries, reducing follower and following payloads by 99.7%.

At University of Illinois Urbana-Champaign, I’m developing an LLM- and knowledge-graph-driven personalized learning system, and at AI Alignment @ Illinois I built a multi-agent debate framework that improved GSM8K mathematical reasoning accuracy by more than 40%. Previously, I developed backend systems at Tripalink and stateful LLM infrastructure at VideoTutor, including retrieval and model routing for a product that reached 30K+ users.

Experience

Work history, roles, and key accomplishments

Current

Graduate Research Assistant

Current

University of Illinois Urbana-Champaign

Aug 2026 - Present (3 months)

- Developing and deploying an LLM- and knowledge-graph–driven personalized learning system on Illinois Chat, UIUC’s production-grade AI platform, structuring course knowledge to support grounded, adaptive feedback for students.
- Extending the deployed system toward course-specific assessment workflows and PrairieLearn/Canvas integration, enabling classroom pilots across different engineering disc

Current

Machine Learning Researcher

Current

AI Alignment @ Illinois

Jan 2026 - Present (10 months)

Research Focus: Investigated "Majority Error" and "Consensus Drift" phenomena in Large Language Models, focusing on the "AI Safety via Debate" paradigm to enhance factual truthfulness over popularity bias.

Multi-Agent Architecture: Engineered a sophisticated Multi-Agent Debate (MAD) framework utilizing role-specialized personas (e.g., Debater vs. Opponent). This system forces competing LLMs to ar

Software Engineer

The Paddock

Aug 2026 - Sep 2026 (1 month)

- Owned the product-wide expansion from a car-only domain to multi-vehicle support, extending NHTSA-backed ingestion and merge pipelines, PostgreSQL schemas, Flutter data models, and user-facing workflows to ship end-to-end motorcycle support while preserving backward compatibility with existing automotive features.

- Re-architected the social graph data layer across Flutter, Supabase, PostgreSQL

Volunteer Software Engineer

The Rabbit Haven

Nov 2021 - Jul 2025 (3 years 8 months)

Full-Stack Modernization: Reconstructed the organization's legacy web portal using React.js, digitizing animal profile management workflows and significantly improving cross-functional collaboration.

ETL & Data Engineering: Built an automated Python-based ETL data pipeline for data cleaning and synchronization into a MySQL database, reducing manual operational overhead by 80%.

Concurrency Contro

Co-founder/Machine Learning Engineer

VideoTutor

Nov 2023 - Oct 2024 (11 months)

Strategic Pivot & Product Leadership: Led the strategic architectural pivot from Kimi.ai’s generalized assistant model to CollegeBot.ai, an academically specialized LLM mentor, addressing critical market needs for reliable, hallucination-free educational AI.

LLM Routing & Cost Optimization: Deployed a dynamic LLM routing classifier via LangChain to evaluate user query complexity in real-time. By

Software Engineer Intern

Tripalink

Jun 2023 - Aug 2023 (2 months)

Microservices Architecture: Architected and deployed a scalable microservices backend using Java, Spring Boot, and GraphQL to power an AI-driven apartment rental recommendation engine. Deployed and managed runtimes across AWS infrastructure (EC2, EKS).

API & Latency Optimization: Designed and delivered RESTful APIs that accelerated the Data Science team's tenant analysis workflows by 80%.

Databa