Jenish Kothari

About

Software engineer who likes hard problems and small models that overperform.

8–4: System design @ Adobe. Authorization infra and asset approval workflows that stay fast and correct at enterprise scale.

4–10: Post-training LLMs + agentic AI. Recently fine-tuned a 7B model to beat Grok-4 on Text-to-SQL for $25.

Building

VibeSec, a security benchmark for AI-generated code. 1,000 tasks, each a stable URL carrying the prompt, the generated app, an exploit that proves the bug, and a reference patch. Frontier models are scored on whether the code they write survives it.

Interests

Achievements

Jenish and two teammates on stage holding a $2,000 cheque at Confluent AI Day 2025
Confluent AI Day 2025
Jenish and a teammate receiving a $1,000 cheque at AI Builder Day
AI Builder Day
Group photo of the Build with Gemma hackathon participants
Build with Gemma

Competitive programming

Codeforces · 93 contests since 2024 · peak 1618, now 1435
500 1000 1600 Expert 1435 2024 2026
LeetCode · 122 contests since 2021 · peak 2166, now 2162
1500 2000 2500 2162 2021 2026

Writing

Post-trainingThe starting line: a 7B against the frontier · 6 Nov 2026
Part 2 of Post-Training 101. Qwen2.5-Coder-7B with no training, next to three much larger models, with and without BIRD's evidence hint, and how far each score can be trusted.
Post-trainingUnderstanding the data and the benchmark · 25 Oct 2026
Part 1 of Post-Training 101. Why I am post-training a 7B model to write SQL, what I want to learn along the way, and a first look at BIRD, the benchmark it will be graded on.
InterviewsTwo rounds at Stripe, and one part short · 6 Oct 2026
A cold application to Stripe's new grad Software Engineer role in November 2025. A hard four-part online assessment, then an interview in the same format where I finished three parts of four. The biggest mistake was the language I chose.
InterviewsTwo rounds at Meta, and a rejection within the hour · 5 Oct 2026
A cold application to Meta's 2026 Production Engineer University Grad role. Two screen rounds on systems fundamentals and coding, a rejection within an hour of finishing, and then silence.
InterviewsFour rounds at ServiceNow, and results that came too late · 3 Oct 2026
The ServiceNow SWE internship loop for summer 2025. A recruiter screen, then three 30 minute interviews in one afternoon covering systems design, two LeetCode mediums and containers. The results were slow to come back, and by then I had already said yes to Adobe.

Elsewhere

Start here · Projects · About

GitHub · Hugging Face · X · LinkedIn · kotharijenish2001@gmail.com