# Sadiya B. > Sr. Software Engineer · Agentic AI Systems · LLMs · React · TypeScript Location: Livermore, California, United States Profile: https://flows.cv/sadiya I build software that makes AI do the heavy lifting. Over the past 6 years, I've worked across the full stack, from React frontends to cloud infrastructure, but the work I'm most energised by is at the intersection of LLMs and real product problems. Right now I'm at ELB US, where I architected a text-to-SQL pipeline that takes a natural language question, decomposes it, retrieves context from a vector store, generates and validates a SQL statement, and returns a formatted response, all autonomously. Before that, at HomePulse.ai, I integrated AI agents to automate document parsing and data extraction at scale. What I bring to an AI startup: - I've shipped LLM-powered features in production, not just prototypes - I think in systems: how do you validate AI output before it hits a database? How do you handle edge cases when the model gets it wrong? - I'm comfortable owning a feature end-to-end, from prompt design to the React component the user sees I'm based in the Bay Area and actively looking for my next role at an early-to-mid stage AI startup where the engineering team is still figuring out how to build reliably with LLMs. That's the problem I want to work on. If you're building in that space, let's talk. ## Work Experience ### Software Engineer @ ELB US Inc. Jan 2025 – Present | California, United States - Architected a text-to-SQL + RAG pipeline with intelligent routing, dynamically switching between SQL and RAG vector stores based on query intent, serving 150 users across read and summarization workflows, with write-phase agentic execution (natural language → invoice generation) currently in development. - Eliminated ~20 hours of manual data entry per fortnight for a 2-person ops team by processing 100+ invoices weekly through AI-driven document extraction, replacing typed input with a single-click confirmation flow. - Built a query complexity scoring layer that routes to Gemini Pro above a 65% complexity threshold and base models below, optimizing inference costs without degrading output quality. - Designed human-approval gates into the pipeline to validate generated SQL before execution, preventing unsafe queries from reaching the database ### Senior Software Engineer @ HomePulse.ai Jan 2025 – Jan 2025 | California, United States - Led product growth engineering initiatives, including onboarding video scripting and nurture funnels, resulting in 40% faster onboarding, 30% reduction in user drop-off, and 35% fewer support inquiries. - Revamped cost analysis algorithms for recurring expenses, mortgage, utilities, and insurance, using JavaScript and MongoDB, increasing user engagement by 70% through improved financial tracking in weekly digest emails. ### Software Engineer @ HomePulse.ai Jan 2024 – Jan 2025 | California, United States - Owned end-to-end development of a Comparable Search feature (React, Node.js, MongoDB), enabling interactive filtering and comparison of insurance providers, contractors, and listings, driving 40% increase in user engagement and becoming one of the platform's most-used tools. - Integrated TensorLake (Indexify) Document APIs to automate parsing of HTML, PDFs, and structured data, reducing manual data entry by 90% and cutting error rates to near zero across 600+ user profiles. ### Software Engineer @ CrowdDoing Jan 2023 – Jan 2024 In my role as a Software Engineer at CrowdDoing, I spearheaded the development of a Wildfire Prevention website using React and Node.js. Leveraging MongoDB Atlas, I optimized data management and outreach efforts. Implementing a CI/CD pipeline, I automated deployment processes for faster website updates. ### Software Engineer Intern @ Cisco Jan 2023 – Jan 2023 | San Francisco, California, United States In my role as a Software Engineer Intern at Cisco, I developed a real-time Agent Tracking UI using TypeScript and Spring Boot, improving developer productivity and reducing manual SQL querying and tracking. I also created a gRPC-based API for agent proxy listing, offering users real-time visibility and control over their proxies while ensuring codebase quality through integration testing. ### Graduate Teaching Assistant @ Northeastern University Jan 2021 – Jan 2022 | United States ### Instructional Assistant @ Northeastern University Jan 2021 – Jan 2021 | Silicon Valley, California, United States ### Software Engineer @ Avalara Jan 2018 – Jan 2020 | India • Developed and implemented an automated tax form filing system using iTextSharp and SQL, integrating 250+ tax forms seamlessly. • Optimized sales and tax data collection process, reducing tax document creation time from 2 weeks to 1 day. • Merged 8 functionally similar applications into 3, reducing customer dissatisfaction by 30%. ### Intern @ Avalara Jan 2018 – Jan 2018 | Pune Area, India In my role as an Intern at Avalara, I implemented automated processes for tax filings, developed internal products for GST tax filling automation, and constructed secure APIs for data access with extensive authorization procedures. These initiatives resulted in significant time and cost savings, a 98% reduction in manual entry checking time, and a 99% uptime rate for data access. ## Education ### Master of Science - MS in Computer Science Northeastern University ### Bachelor of Technology in Information Technology Vishwakarma Institute Of Technology ### Diploma in Information Technology AISSMS POLYTECHNIC ## Contact & Social - LinkedIn: https://linkedin.com/in/sadiya-bhawania --- Source: https://flows.cv/sadiya JSON Resume: https://flows.cv/sadiya/resume.json Last updated: 2026-04-10