{"$schema":"https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json","basics":{"name":"Dhruv Patel","label":"Research Assistant – Robotics & Reinforcement Learning","image":"https://saywise-production-profilepicturestoragebucket-kbfooccc.s3.amazonaws.com/profile-pictures/1728d754-a8d6-4c0b-9ddc-5950105f25e5/linkedin-1790800749634.jpg","summary":"Robotics engineer building cross-embodiment learning systems and sim-to-real pipelines for humanoids, quadrupeds, and manipulators; expertise in teleoperation, VLA/RL evaluation, and hardware debugging.","location":{"city":"San Jose, CA, United States"},"profiles":[{"network":"LinkedIn","username":"dhruvpatel16","url":"https://linkedin.com/in/dhruvpatel16"},{"network":"GitHub","username":"pateldhruv1672","url":"https://github.com/pateldhruv1672"},{"network":"Portfolio","username":"pateldhruv1672.github.io","url":"https://pateldhruv1672.github.io"}]},"meta":{"canonical":"https://saywise.com/member7245","version":"v1.0.0","lastModified":"2026-09-30T20:42:28.268Z"},"x_saywise":{"handle":"member7245","pronouns":null,"availability":null,"oneLiner":"Robotics engineer building cross-embodiment learning systems and sim-to-real pipelines for humanoids, quadrupeds, and manipulators; expertise in teleoperation, VLA/RL evaluation, and hardware debugging.","profileUrl":"https://saywise.com/member7245","markdownUrl":"https://saywise.com/member7245/profile.md","pdfUrl":"https://saywise.com/member7245/resume.pdf","archetype":{"code":"HS-MG","name":"Launchpad Trailblazer","url":"https://saywise.com/sca/6c181aae6fc8","rarity":"One of the first Launchpad Trailblazers on Saywise"},"aiStack":[{"name":"Claude","description":"My daily driver for coding and brainstorming ideas","url":"https://claude.ai","storyCount":0}]},"work":[{"name":"San José State University","position":"Research Assistant – Robotics & Reinforcement Learning","location":"San Jose, CA","startDate":"2026-01-01","summary":"Built a training-to-robot loop for Unitree G1 humanoid, Go2 quadruped, and xArm7 that collects teleoperation and joint-state data, trains PPO/behavior-cloning policies in Isaac Lab, runs simulation gates, and deploys to hardware—cutting setup time from 90 to 30 minutes. Instrumented RGB-D, IMU, and joint-state logs with shared timestamps and offline replay to isolate DDS packet loss, frame calibration drift, and joint-limit violations, reducing debugging turnaround from 45 to 15 minutes."},{"name":"Applied Intelligent Systems at SJSU","position":"President | Applied Intelligence Systems (AIS) Club","startDate":"2025-12-01","summary":"As President of the AIS Club, I drive initiatives that enhance member engagement and professional growth. • Spearheaded the planning and execution of events and workshops tailored to member interests and industry trends. • Fostered collaboration with faculty and alumni to provide networking opportunities and professional development resources. • Developed strong communication strategies to gather feedback and streamline event planning processes."},{"name":"Bain & Company","position":"Senior Associate Software Engineer (AI/ML)","location":"New Delhi, Delhi, India","url":"https://bain.com","startDate":"2024-04-01","endDate":"2025-07-01","summary":"Fine-tuned Mistral-8B and integrated RAG over Bain's presentation corpus for a slide-generation workflow, automating template selection and data population to deliver 40% productivity gain. Built distributed PySpark/Redshift pipelines processing 1 TB+ daily with schema validation, idempotent execution, and alerting—reducing pipeline rework by 60%. Deployed W&B experiment tracking and CloudWatch observability across 50+ experiments, cutting incident triage from 40 to 20 minutes."},{"name":"Samsung R&D Institute India","position":"Research And Development Engineer","location":"Noida, Uttar Pradesh, India","startDate":"2022-06-01","endDate":"2024-04-01","summary":"Led R&D for an instruction-based image-editing system combining LLM instruction parsing with Stable Diffusion, optimizing inference by 250 ms for interactive use. Prototyped real-time English-to-Hindi translation and automated reply generation achieving 450 ms inference for bilingual voice interactions. Profiled and debugged a production LLM image-editing service, reducing p99 latency from 1.2 s to 480 ms through batching, async execution, and resource optimization. Deployed on-device ML models using quantization and knowledge distillation, reducing model size by 60% while preserving 98%+ accuracy."},{"name":"Wipro Limited","position":"Software Engineer Intern","location":"India","url":"https://wipro.com","startDate":"2021-06-01","endDate":"2021-07-01"},{"name":"Edulyt India","position":"Data Analyst Intern","startDate":"2020-06-01","endDate":"2020-08-01"},{"name":"Sardar Vallabhbhai National Institute of Technology, Surat","position":"Research Intern","location":"Surat Area, India","startDate":"2019-12-01","endDate":"2020-02-01"}],"education":[{"institution":"San José State University","studyType":"Master of Science - MS in Applied Data Intelligence","startDate":"2025-08-01","endDate":"2027-05-01"},{"institution":"Sardar Vallabhbhai National Institute of Technology, Surat","studyType":"Bachelor of Technology - BTech in Electronics and Communication Engineering","startDate":"2018-06-01","endDate":"2022-05-01"}],"projects":[{"name":"The Last Degree – Graduate ROI Intelligence","description":"An end-to-end intelligence platform that bridges the gap between educational investment and job market reality. By unifying university data, live job listings, and layoff trends, the platform provides data-driven career insights via a modern web interface and an AI-powered SQL agent. Technical Overview: Backend & Data Engineering: Orchestrated complex ETL/ELT pipelines using Apache Airflow to ingest and unify disparate university, Adzuna job market, and BLS datasets into Snowflake. Resolved data fragmentation by implementing fuzzy-joins and lookup tables for missing primary keys. AI & Analytics: Architected an LLM-based SQL Agent to allow natural language querying of complex ROI datasets. Integrated an Apache Superset dashboard for enterprise-level visualization of layoff trends and market volatility. Frontend & UI/UX: Developed a high-performance, responsive interface (https://thelastdegree.dev/) to visualize Graduate ROI ratios, active job distributions, and real-time WARN notice trends. Key Achievement: Created a unified data model across 6,400+ institutions and 21k+ active job listings to calculate real-time career \"Return on Investment.\""},{"name":"Humanoid Teleoperation & Multimodal Robot Data Pipeline","description":"Built a Rokoko-to-robot teleoperation pipeline streaming 60 Hz body/hand pose into ROS 2, retargeting motion to the Unitree G1 humanoid and BrainCo Revo2 hand. Collected 120 episodes with 30 Hz RGB video, 60 Hz human pose, robot joint state, and hand commands, maintaining timestamp alignment and dropped samples below 1%. Added one-click calibration, Wi-Fi/DDS health checks, and packet-age alerts to isolate connection faults without full-stack restarts."},{"name":"Vision-Language Navigation & Persistent Semantic Memory","description":"Built a Unitree Go2 vision-language navigation stack that parses natural-language commands, grounds objects in RGB-D observations, associates detections with map coordinates, and sends goals to Nav2—reaching correct landmarks in 50/60 scripted trials. Implemented persistent semantic memory storing object labels and embeddings; on revisits, retrieved previously seen targets 88% of the time versus 63% with only current observations. Classified failure modes and replayed them in Isaac Sim, tuning confidence thresholds and waypoint validation to raise success from 68% to 83%."},{"name":"Cross-Embodiment RL & Sim-to-Real Policy Evaluation","description":"Explored COMPASS residual-RL adaptation in Isaac Lab for Unitree G1 humanoid and Go2 quadruped: kept base velocity policy frozen and trained PPO residual corrections for embodiment-specific dynamics, comparing goal success and collision rate over 100 episodes per checkpoint. Applied domain randomization across mass, friction, sensor noise, and command latency for manipulation policies, reducing sim-only failures and improving physical xArm7 transfer success from 62% to 78%."}],"skills":[{"name":"Physical AI"},{"name":"SLAM"},{"name":"Motion Control"},{"name":"Visual SLAM"},{"name":"Robotics"},{"name":"Data Build Tool (DBT)"},{"name":"Airflow"},{"name":"Docker"},{"name":"React.js"},{"name":"Snowflake"},{"name":"Retrieval-Augmented Generation (RAG)"},{"name":"Systems Design"},{"name":"Natural Language Processing (NLP)"},{"name":"Computer Vision"},{"name":"Research and Development (R&D)"},{"name":"Large Language Models (LLM)"},{"name":"Distributed Systems"},{"name":"Generative AI"},{"name":"Generative Adversarial Networks (GANs)"},{"name":"Python"},{"name":"C++"},{"name":"Java"},{"name":"SQL"},{"name":"JavaScript/TypeScript"},{"name":"ROS 2"},{"name":"Nav2"},{"name":"Unitree SDK2"},{"name":"xArm7"},{"name":"NVIDIA Isaac Lab"},{"name":"Isaac Sim"},{"name":"Sim-to-Real"},{"name":"ROS Bags"},{"name":"Reinforcement Learning"},{"name":"Behavior Cloning"},{"name":"Imitation Learning"},{"name":"Vision-Language-Action (VLA)"},{"name":"Teleoperation"},{"name":"Motion Retargeting"},{"name":"RGB/RGB-D Cameras"},{"name":"Depth Sensors"},{"name":"LiDAR"},{"name":"IMU"},{"name":"Camera Calibration"},{"name":"OpenCV"},{"name":"PyTorch"},{"name":"CUDA"},{"name":"TensorRT"},{"name":"NVIDIA Jetson"},{"name":"Quantization"},{"name":"W&B"}],"certificates":[{"name":"Lean Six Sigma for a Sustainable Future","date":"2023-08-01","issuer":"LinkedIn"},{"name":"Mastering Model Context Protocol (MCP)","date":"2025-09-01","issuer":"LinkedIn"},{"name":"Software Architecture Foundations","date":"2022-08-01","issuer":"LinkedIn"},{"name":"Applied Data Science Capstone","date":"2020-05-01","issuer":"Coursera"},{"name":"IBM Data Science Professional Certificate","date":"2020-05-01","issuer":"Coursera"},{"name":"Data Visualization with Python","date":"2020-05-01","issuer":"Coursera"},{"name":"Structuring Machine Learning Projects","date":"2020-04-01","issuer":"Coursera"},{"name":"Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization","date":"2020-04-01","issuer":"Coursera"},{"name":"Machine Learning(Stanford Online)","date":"2020-04-01","issuer":"Coursera"},{"name":"Data Analysis with Python","date":"2020-04-01","issuer":"Coursera"},{"name":"Programming Foundations with JavaScript, HTML and CSS (with Honors)","date":"2020-04-01","issuer":"Coursera"},{"name":"Databases and SQL for Data Science","date":"2020-01-01","issuer":"Coursera"},{"name":"Machine Learning with Python","date":"2020-01-01","issuer":"Coursera"},{"name":"Python for Data Science and AI","date":"2019-12-01","issuer":"Coursera"},{"name":"Python for Data Science and AI","date":"2019-12-01","issuer":"Coursera"},{"name":"Google Cloud Platform Fundamentals: Core Infrastructure","date":"2019-12-01","issuer":"Coursera"},{"name":"Technical Support Fundamentals","date":"2019-12-01","issuer":"Coursera"},{"name":"Neural Networks and Deep Learning","date":"2019-12-01","issuer":"Coursera"},{"name":"Data Science Methodology","date":"2019-12-01","issuer":"Coursera"},{"name":"Data Science Methodology","date":"2019-12-01","issuer":"IBM"}]}