Shiv Ratan Choudhary
Engineering @ Regie.ai | 5* @ CodeChef (2040) | NIT Srinagar | Software Engineer
Nagaur
2+ years of work experience
Jan 20266 moJul 2026
Bengaluru, Karnataka, India
◦ Revamped research agent architecture, reducing API calls by 67% (3 to 1 per query) and saving over $20,000 per month in
inference costs, while cutting per-request cost by 90% and improving response latency by 75%.
◦ Built a high-scale async research engine using Python AsyncIO with 150 concurrent workers, SQS batch processing
(100/msg), Redis distributed locks, exponential backoff retries, DAG-based orchestration, and multi-level caching;
processing millions of datapoints weekly.
◦ Deployed three specialized research pipelines tailored to distinct query categories, increasing retrieval relevance by 22%,
improving factual coverage, and boosting overall answer quality across production workloads.
◦ Engineered a cross-service credit deduction pipeline across three microservices through checkpoint-based aggregation and
idempotent upserts, eliminating duplicate charges while synchronizing balances within 60 seconds.
◦ Devised a comprehensive LLM evaluation framework featuring a two-stage “LLM-as-Judge” architecture with Perplexity
Sonar Pro for web fact verification and GPT-5 for structured evaluation, enabling parallel A/B benchmarking across 8 model variants and cutting manual evaluation effort by 80%.
May 20258 mosDec 2025
Srinagar, Jammu & Kashmir, India
◦ Collaborated and Delivered 15+ production enhancements to React.js interfaces for job recommendations and worker
dashboards, reducing First Contentful Paint from 1.4 seconds to 0.9 seconds and Time to Interactive from 2.4 seconds to
1.6 seconds, achieving Google Lighthouse performance score of 92/100.
◦ Integrated FastAPI-based AI services with frontend components to enable intelligent task matching, boosting
automated assignment accuracy by 18% and reducing manual intervention overhead by 30 hours per week, in collaboration
with cross-functional teams.
◦ Implemented internationalization support for five Indian languages (Hindi, Bengali, Tamil, Telugu, Marathi),
expanding platform accessibility to diverse regional users and increasing engagement metrics by 25%
Dec 20243 mosFeb 2025
Hybrid
Developed a Siamese Neural Network in PyTorch for patient biometric verification, achieving 98.6%+ matching accuracy.
Built a biometric pipeline with PyTorch + FastAPI, reducing manual verification time and streamlining authentication workflows.
Integrated backend services using Node.js (Express.js) and SQL databases to support scalable hospital operations.
Planned and tested integration with hospital systems to automate check-ins for 400+ daily patients, reducing errors and improving efficiency.
Nov 20231 moNov 2023
On-site
Managed the event with team.
Oct 20231 yr 1 moOct 2024
Shiv’s AI Stack
Education
Bachelor of Technology - BTech, Electrical, Electronics and Communications Engineering
National Institute of Technology Srinagar
20224 yrs2026
12th, PCM
Manu Public Sr. Sec. School, Kota
20192 yrs2021
Join Shiv and 10k+ other professionals on
Tal is the app where bosses meet engineers & builders directly, without middlemen
Download Tal Boss