--- title: "Aishwariya Singha Roy - Lead AI Engineer in Bengaluru | Tal" description: "Meet Aishwariya Singha Roy, Senior Backend Engineer who obsesses over simplicity at scale | Agentic AI & distributed systems @ Spectatr.ai | Ex-Amazon based in Bengaluru. AI stack includes cursor, hugging face, and langchain." image: "https://tal.club/meet/aishwariya-singha-roy/share-image" --- # Aishwariya Singha Roy on Tal ## Headline Senior Backend Engineer who obsesses over simplicity at scale \| Agentic AI & distributed systems @ Spectatr\.ai \| Ex\-Amazon ## About "Over 6 years of experience designing, building, and operating cloud‑based backend platforms and infrastructure, with a focus on reliability, scalability, and observability in production environments\." Hi, I am a Software Development Engineer focused on building reliable, scalable backend systems and production\-grade Agentic AI workflows\. Currently, I work at a B2B startup in the esports domain, where I design, build, and maintain backend platforms serving international clients at scale\. My role involves true end\-to\-end ownership—from system design and architectural decisions to implementation, optimization, and handling real\-world production challenges\. At work, you’ll often find me discussing or teaching the latest developments in AI or diving deep into database internals—the latter being my favorite rabbit hole\. A significant part of my current work centers around Agentic AI systems, where I design workflows in which autonomous agents reason, act, coordinate, and integrate seamlessly with backend services in a controlled, scalable, and observable manner\. I enjoy working at the intersection of traditional backend engineering and applied AI, ensuring that AI\-driven systems are not just intelligent, but also robust, secure, and production\-ready\. On the engineering side, I work extensively on: Backend system design and architecture High\-throughput, low\-latency services SDK and platform integrations for partner applications API design, data flows, and reliability at scale Applying AI agents within real business workflows \(not demos\) I care deeply about clean architecture, performance, and long\-term maintainability\. I enjoy solving ambiguous problems, breaking them down into simple, well\-designed systems, and shipping solutions that actually get used\. I strongly believe that good software engineering is less about clever hacks and more about making systems boringly reliable\. Open to discussions around backend engineering, Agentic AI, and scalable system design\. ## Location Bengaluru ## AI stack cursor hugging face langchain langgraph ## Work experience Lead AI Engineer at SPECTATR\.AI, May 2025 \- Present · 1 yr, Gurugram, Haryana, India, \* Architected an enterprise\-grade AI chatbot ecosystem: 6\+ specialized agents built using LangGraph state\-machine orchestration, policy\-based guardrails, and rate limiting, establishing the core technical foundation for the company’s AI product line\. • Slashed LLM hallucination by 80% via an automated evaluation and regression pipeline in LangSmith with prompt versioning and continuous refinement loops, directly improving production reliability\. • Defined and owned an LLM\-powered hyper\-personalization engine, persisting long\-term user memory in Mem0 backed by Qdrant vector search, extracting structured profiles to serve personalised content across 4 surfaces — articles, videos, polls, and trivia — via a precomputed feed with Bloom filter deduplication, delivering a cohesive per\-user experience at scale\. • Spearheaded all cross\-cutting technical decisions: model selection, cost\-performance tradeoffs, vector search tuning, and conditional agent routing\. Functioned as the de facto technical lead across AI and backend teams\. • Launched a live\-stream ingestion pipeline for real\-time sports broadcast processing\. Incoming SRT feeds converted to HLS using AWS MediaLive and Lambda, with segment storage backed by S3, enabling the extraction of downstream highlights at near\-real\-time latency for live match coverage\. SDE\-2 at SPECTATR\.AI, Mar 2022 \- Apr 2025 · 3 yrs 2 mos, Gurugram, Haryana, India, \* Engineered a change data capture pipeline using Debezium to stream database mutations into the caching layer in near\-real\- time, eliminating manual cache invalidation and ensuring read\-path consistency across 3\+ services\. • Constructed a resumable multi\-part video upload system for the highlights product, tracking per\-chunk integrity via fingerprint hashing in the database ensuring fault\-tolerant, idempotent uploads resilient to network interruptions and partial failures\. • Pioneered a social graph service via dual\-write denormalization and Redis sorted sets for sub\-ms retrieval\. Streamlined atomic, single\-shard query resolution, catalyzing a 25% surge in social discovery and a 12% lift in Day\-30 retention\. • Consolidated payment orchestration for 3\+ product lines \(B2B, D2C, SaaS\), integrating Stripe, GCash, and Razorpay\. Engineered automated post\-match ticket reconciliation and SNS/SQS\-driven settlement with zero\-downtime failover, ensuring real\-time transaction visibility for global and domestic users\. • Forged a behavioral segmentation engine over user engagement signals, and a gamified in\-app currency system powering targeted retention campaigns, yielding a 30% improvement in user retention rates and engagement frequency\. SDE at Amazon, Jun 2019 \- Feb 2022 · 2 yrs 9 mos, Hyderabad, Telangana, India, \* Developed and maintained backend services that handle high\-traffic customer quote data using the MVC framework with Spring Boot\. • Built a notification platform hosted on EC2, consuming SQS event streams to trigger customer notifications across multiple channels\. • Managed AWS resources including EC2, CloudFormation, and SQS, ensuring the scalability and observability of production systems\. • Resolved multiple critical and high\-severity issues during on\-call rotations, maintaining SLA compliance and platform reliability\. Technical Member at Coding Club NIT Silchar, Feb 2016 \- Apr 2019 · 3 yrs 3 mos, Silchar, Assam, India ## Education Bachelor’s Degree, Computer Engineering, National Institute of Technology Silchar Engineer's degree, Android Development, RCPL [View the original profile](https://tal.club/meet/aishwariya-singha-roy) ```json { "@context": "https://schema.org", "@graph": [ { "@type": "Person", "@id": "https://tal.club/meet/aishwariya-singha-roy#person", "name": "Aishwariya Singha Roy", "url": "https://tal.club/meet/aishwariya-singha-roy", "image": "https://tal.club/meet/aishwariya-singha-roy/profile-photo.jpg", "description": "Meet Aishwariya Singha Roy, Senior Backend Engineer who obsesses over simplicity at scale | Agentic AI & distributed systems @ Spectatr.ai | Ex-Amazon based in Bengaluru. AI stack includes cursor, hugging face, and langchain.", "jobTitle": "Lead AI Engineer", "worksFor": { "@type": "Organization", "name": "SPECTATR.AI" }, "hasOccupation": { "@type": "Occupation", "name": "Lead AI Engineer" }, "homeLocation": { "@type": "Place", "name": "Bengaluru" }, "alumniOf": [ { "@type": "EducationalOrganization", "name": "National Institute of Technology Silchar" }, { "@type": "EducationalOrganization", "name": "RCPL" } ], "knowsAbout": [ "cursor", "hugging face", "langchain", "langgraph" ], "mainEntityOfPage": { "@id": "https://tal.club/meet/aishwariya-singha-roy#webpage" } }, { "@type": "ProfilePage", "@id": "https://tal.club/meet/aishwariya-singha-roy#webpage", "url": "https://tal.club/meet/aishwariya-singha-roy", "name": "Aishwariya Singha Roy on Tal", "description": "Meet Aishwariya Singha Roy, Senior Backend Engineer who obsesses over simplicity at scale | Agentic AI & distributed systems @ Spectatr.ai | Ex-Amazon based in Bengaluru. AI stack includes cursor, hugging face, and langchain.", "dateModified": "2026-07-21T18:54:56.879Z", "isPartOf": { "@id": "https://tal.club/#website" }, "mainEntity": { "@id": "https://tal.club/meet/aishwariya-singha-roy#person" }, "primaryImageOfPage": { "@type": "ImageObject", "url": "https://tal.club/meet/aishwariya-singha-roy/profile-photo.jpg", "contentUrl": "https://tal.club/meet/aishwariya-singha-roy/profile-photo.jpg", "caption": "Aishwariya Singha Roy profile photo on Tal" }, "inLanguage": "en-IN" } ] } ```