# Kshitij Khare > Voice AI Agents | Healthcare & Real Estate Location: San Francisco, California, United States Profile: https://flows.cv/kshitijkhare I’ve spent most of my life trying to understand how systems behave when they are pushed. In high school it was small projects, scripts, experiments that usually broke before they worked. But that habit stayed. I liked taking ideas apart until I understood the constraints, then rebuilding them so they ran better than before. That same instinct is what drives my work now. I build CC/CD pipelines that help multimodal AI systems run with very low latency and behave predictably in production. My days revolve around evals, tool-calling, and versioning because the difference between a demo and a real product is not how it speaks, but how reliably it performs when conditions change. I started in healthcare, working on agents that handled scheduling and insurance workflows. It forced me to think about compliance, privacy, and failure states long before everyone started talking about “AI safety”. That experience shaped how I design systems today. Over the last quarter I’ve been building more advanced agents that integrate directly with operational tools across office suites and property management systems. If you want a sense of the direction I’m exploring, you can look at JusDials.com. A lot of what I think about is the line between autonomy and control. Giving an agent many tools doesn’t automatically make it useful. What matters is how it decides when to act, how much freedom it has, and what constraints keep its behavior aligned with the environment it’s operating in. Getting that balance right is part engineering, part product thinking, and part intuition built from shipping real systems. If you’re solving similar problems, or you want to talk about how AI agents can fit into actual business workflows, Let's Talk! Just an email away - kshitijkharework@gmail.com I enjoy these conversations and they usually lead to something interesting! :D ## Work Experience ### Full Stack AI Engineer (Founding) @ Deep MindScape Jan 2025 – Present | New York City Metropolitan Area I built DeepMindScape as an applied-AI lab focused on designing production-grade voice automation systems across multiple industries. I developed end-to-end voice pipelines — real-time ASR, LLM agents, TTS, evaluation harnesses, and monitoring — for two major verticals: healthcare and real estate. On the healthcare side, I engineered voice agents that handled patient intake, scheduling, insurance checks, billing/coding support, and RCM workflows. Separately, I built a second suite of voice agents for property management and leasing (check out www.JusDials.com), including multilingual leasing assistants, maintenance triage, tour scheduling, and resident support. Both verticals operate on independent architectures tailored to their domain, but I unified them through MCP servers and tool-calling layers that integrate with PMS systems, software suites, and external APIs for actions like scheduling, ticket creation, data retrieval, and policy lookup. This involved: • Designing real-time voice pipelines for domain-specific intents • Developing MCP servers to integrate with PMS/RCM/CRM systems • Building knowledge-base ingestion + structured retrieval for each vertical • Architecting agent behaviors, business-rules execution, and persona design • Creating evaluation + calibration systems for call quality and reliability ### Software Engineer (Founding) @ BulkMagic Jan 2024 – Jan 2025 | New York City Metropolitan Area • Architected a scalable software architecture of an E-commerce platform on AWS • Developed a complex pricing algorithm to reduce the realtime browsing latency, trained on over 10M tuples of categorically sorted historical data • Built a search indexing based chatbot to resolve platform related queries of cusotmers • Worked on the social marketing side -- video editing, promotional content creation for the social media platforms • Participated in connecting with vendors, onboarding them and getting the SLAs in place ### Artificial Intelligence Engineer @ Reality AI Lab Jan 2023 – Jan 2023 | New York City Metropolitan Area • Developed an IT skills training chatbot starting with prompt engineering and OPENAI's API. • Achieved a 94.8% improvement rate in user skill levels, measured through SentenceTransformer's training data. • Implemented advanced Large Language Models (LLMs) such as LLaMA2 and BART with vectorization techniques to minimize API reliance. • Constructed a chatbot utilizing LLaMa2's pre-trained model with 7 billion parameters. • Conducted hyperparameter tuning, including temperature=0.7, top-p=0.8, top-k=40, and max_tokens=512, for optimal chatbot performance. ### Data Visualization Engineer @ Cognizant Jan 2022 – Jan 2022 | India • Developed and implemented shell scripts to automate program execution, facilitate file manipulation, and generate text outputs, resulting in increased operational efficiency. • Acquired proficiency in data visualization tools such as Tableau and Power BI, utilizing them to analyze and present complex data sets. • Spearheaded the creation of a comprehensive sales dashboard on Tableau, enabling real-time monitoring and analysis of product sales performance, contributing to informed decision-making processes within the company. ### Lab ambassador @ The Fab Foundation Jan 2021 – Jan 2022 | India • Organized multiple faculty development programs(FDPs) on fabrication • Supervised several projects and guided students to build a robust system for their projects and startups ### Co-Founder and President @ Team-EAGLE Jan 2020 – Jan 2022 • Built an all-weather drone delivery system with the maximum occupancy of 2 kg freight • Supervised the project - "Obstacle avoidance drone" and built a robust system to avoid any obstacle in the range of 100 cm • Fabricated a 100cm long RC aircraft and successfully made a flight time of 8 minutes • Documented and submitted to DRDO - Two projects named "Vitaran" and "Chakshu" (Cannot share the details due to the government protocols) ### Project Developer @ AKGEC SKILLS FOUNDATION Jan 2019 – Jan 2022 - Worked on BOSCH PLCs and provided automation solutions - Motivated and made aware more students to learn and complete courses offered by AKGEC SKILLS foundation ### Data Scientist @ CRIS; A Autonomous Society under the Ministry of Indian Railways Jan 2021 – Jan 2021 | Delhi, India - Designed a regression model to predict the freight demand of particular commodities - Incorporated the logit models and let sigmoid function decide the commodity - Developed the logistic regression to predict the size of the order ## Education ### Master of Science - MS in Computer Engineering New York University ## Contact & Social - LinkedIn: https://linkedin.com/in/kshitij-khare2 --- Source: https://flows.cv/kshitijkhare JSON Resume: https://flows.cv/kshitijkhare/resume.json Last updated: 2026-04-05