Jun 2024 – Sep 2025 · 1 yr 3 mos · Gurugram, Haryana, India · On-site

• Designed and implemented an AI Gateway to streamline LLM access for 500+ engineers, handling metadata, load balancing, rate limiting, and retries, achieving 99.9% uptime and ≤ 100ms latency handling 10K+ RPM.
• Contributed to development of a real-time AI streaming system supporting 200+ concurrent sessions, cutting message latency by 40% and boosting user experience.
• Built a prompt management system decoupling prompts from deployment pipelines, handling 1000+ prompts across 100+ projects, reducing release overhead by 50%, and amplifying LLM app scalability.
• Implemented an AI Assertions Insights service with real-time citations, scalable entity management, and policy-driven moderation handling.
• Automated AI cost-reporting pipeline across 4 tenants, 100+ projects, and 6 LLM providers, eliminating manual reporting entirely.
• Leveraged audio-to-text models for transcriptions & CSAT inference, identifying potential users for targeted ads.
• Designed and implemented an AI-powered system to create pre-generated product carts tailored to user’s preferences. The solution optimized for cuisine type, budget, occasion, and special requests, delivering ready-made shopping carts for an enhanced and personalized user experience.

Apr 2024 – May 2024 · 1 mo · Gurugram, Haryana, India · On-site

• Developed Prompt dashboard to store & version prompt artifacts, decoupling prompt lifecycle from code releases.
• Engineered Classifier for scalable topic modeling & classification of large datasets into user-defined classes.
• Leveraged audio-to-text models for transcriptions & CSAT inference, identifying potential users for targeted ads.

Nov 2023 – Apr 2024 · 5 mos · Bengaluru, Karnataka, India · Hybrid

• Spearheaded development for Draw 4, a cross-country game from the Node end, incorporating fresh functionalities.
• Implemented queue-based task schedulers using Bulljs over Redis’s key-based scheduling improving reliability.
• Successfully optimized server response time by revamping GRPC calls, enhancing efficiency, & overall performance.
• Tech Stack: NodeJs, Typescript, Redis, Kibana, AWS, Docker

May 2023 – Nov 2023 · 6 mos · Bengaluru, Karnataka, India · Hybrid

• Worked with the Video-KYC team to build and maintain the unassisted VKYC product.
• Engineered a codebase leveraging playwright, resulting in a reduction in sanity & regression testing.
• Conducted and documented multiple POCs exploring and validating innovative solutions.
• Tech Stack: Typescript, React, Playwright, NodeJs, CSS, Angular, Docker

May 2023 – Nov 2023 · 6 mos · Una, Himachal Pradesh, India · On-site

• Overseeing and managing the college's Career Development Cell (CDC), facilitating seamless communication between students, faculty, and recruiters.
• Collaborated with the alumni network to create a bridge between current students and successful alumni, fostering mentorship and internship opportunities.
• Pioneered a mentorship program that paired students with industry professionals, providing invaluable insights and networking opportunities.

Jan 2023 – Apr 2023 · 3 mos · Bengaluru, Karnataka, India · On-site

• Worked with core team to develop the version-II of Juntrax - a HRMS ERP Software.
• Handled an entire Portal also rewrote the base level models of modules.
• Optimised state variables by memoizing, reduced query time and API response time significantly by using cache memories.

Dec 2021 – Jan 2022 · 1 mo · Bengaluru, Karnataka, India · Remote

• Tailored an interactive and responsive website with extensive features.
• Introduced a feature which let users contact the administrator in a very unique manner.
• Engineered frontend solutions, also Overhauled and Diagnosed Bugs during Development.