Jash Parmar
@jash2884
I build software-engineering benchmarks for AI coding agents, reliable LLM evaluation systems, and full-stack products.
IndiaWhat I'm looking for
I'm contributing to Project Sentinel Ultra, Terminus 3, and Project Dynamo by building advanced software engineering benchmark tasks for frontier AI coding agents. I create Harbor-format tasks, Docker-based environments, oracle implementations, deterministic verifiers, automated evaluation pipelines, and test suites.
At Xelron AI, I supported Terminus, Finch, and Project 1307 with Uber AI Solutions, evaluating Gemini responses and delivering enterprise AI evaluation workflows with distributed teams.
I've also led a responsive golf competition platform at Flitzen Technologies UK Limited, adding subscriptions, QR integration, and Winners’ Circle features. In my LLM-powered smart screen recorder project, I combined OCR, semantic embeddings, vector search, and RAG to let users query historical screen activity in natural language.
Experience
Work history, roles, and key accomplishments
- Developed and evaluated domain-specific prompts to assess the performance of large language models (LLMs)
- Working on hindi production labelling tasks
- Contributed to improving AI understanding of complex ML and reasoning topics through expert review and feedback
- Conducted independent research to support prompt development and evaluation tasks
Advanced AI Engineer
Crossing Hurdles
Jul 2026 - Present (3 months)
Contributed to Project Sentinel Ultra and Terminus 3 by developing advanced software engineering benchmark tasks for evaluating frontier AI coding agents. Designed Harbor-format tasks with oracle implementations, deterministic verifiers, Docker-based environments, and automated evaluation pipelines.
LLM Trainer
Handshake AI
Jul 2026 - Present (3 months)
Contributed to Project Dynamo by authoring complex software engineering benchmark tasks for TerminalBench 2. Built end-to-end evaluation tasks including Docker environments, oracle solutions, deterministic verification pipelines, and automated test suites.
Software Development Engineer Intern
Xelron AI
Feb 2026 - Jun 2026 (4 months)
Contributed to AI evaluation projects including Terminus and Finch through prompt engineering and benchmark evaluation. Worked on Project 1307 with Uber AI Solutions evaluating Gemini responses.
Full-Stack Developer Intern
Flitzen Technologies UK Limited
May 2025 - Jul 2025 (2 months)
Led development of a responsive golf competition platform. Built subscription, QR integration and Winners' Circle features, improving engagement through responsive UI and community-focused features.
Education
Degrees, certifications, and relevant coursework
Indian Institute of Information Technology, Kota
Bachelor of Technology, Computer Science Engineering
2022 - 2026
Grade: 6.94/10
Activities and societies: Vice President, Cultural Society
Pursuing a Bachelor of Technology in Computer Science Engineering with a CGPA of 6.87/10.
Tech stack
Software and tools used professionally
Availability
Location
IndiaAuthorized to work in
Website
jashparmar.comSocial media
Job categories
Interested in hiring Jash?
You can contact Jash and 90k+ other talented remote workers on Himalayas.
Message JashGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
