About
Software engineer in Toronto, working on AI systems and backends. I take the parts of a system where a wrong answer costs something.
That means the gate that decides whether an agent may run a command, the retrieval step that picks what a model sees, the benchmark that says which model to trust, the API other people build on. Currently building ContextBridge, portable memory for LLMs with hybrid retrieval, PII redaction, and an offline eval suite, and Substrate, an MCP server for agent memory and permission-gated execution. Previously built the Forest Growth and Yield Analytics System for scientists at Ontario's Ministry of Natural Resources and Forestry, with a 17-algorithm leakage-aware benchmark on real inventory data.
My defaults: typed interfaces, deterministic behaviour where it matters, numbers that come from a test or an eval, and a README that says what the system does not do yet. The positions on the home page say the same thing with receipts. Open to software engineering roles from January 2027, in Toronto or remote. Eligible to work in Canada.
Education
- Degree
- BSc Computer Science, Trent University, expected December 2026. GPA 4.0 of 4.0.
- Coursework
- Data structures and algorithms, software architecture, database systems, artificial intelligence, operating systems, automata theory.
- Also
- Skip lists, treaps, KD-trees, quadtrees, and lazy tries implemented from scratch for coursework; a C# postfix-expression evaluator.
Contact
- ptirth339@gmail.com
- GitHub
- github.com/TirthPatel6104
- linkedin.com/in/tirthpatel610
- Résumé
- HTML or PDF