Mar 2022 – Aug 2023 · 1 yr 5 mos · Bengaluru, Karnataka, India

• Analysed the performance of the RL agents in the semiconductor field that showcased significant improvements in KPIs
• Built an interactive dashboard that helps the team to compare the critical KPIs between different RL agents and visualize them across time
• Performed the tool modeling analysis on an open-source dataset leading to a journal paper

Apr 2021 – Mar 2022 · 11 mos · Bengaluru, Karnataka, India

• Developed an MVP of fixed-wing flight stack (R&D) in less than three months, that includes: autonomous control in offboard mode of PX4 (SITL, HITL, and real-life), robust simulation with flight dynamics in Gazebo & Unity3D, decentralized collision avoidance algorithms (RVO2), and a communication module with ROS2 & ROS1 bridge
• Built an in-house Ground Control Station software for complex mission planning, obstacle/geofence building, path planning, and status monitoring using PyQt5

Oct 2020 – Mar 2021 · 5 mos · Amsterdam, North Holland, Netherlands

• Built an autonomous robot (Pixie-four wheeled drive) from scratch in Nvidia Isaac SDK
• with custom stereo visual odometry for localization, april tag based relocalization and
• obstacle avoidance in the span of two months
• Achieved a 0.87 IoU score on a bean field dataset (proprietary) by training a SegNet and
• HoughCNet in tandem for crop row detection pipeline

Nov 2019 – Aug 2020 · 9 mos · Amsterdam Area, Netherlands

• Unsupervised domain adaptation for low-resource entity recognition:
• Determined the efficient loss-centric method in unsupervised domain-adaptation of a
• pre-trained transformer (BERT) for entity recognition; performance gain of 3.2 F1 score
• Contributed an extensively pre-processed Enron email dataset and annotation set
• valuable for retrieval and extraction testing purposes at ZyLAB

Jun 2019 – Jul 2019 · 1 mo · Amsterdam Area, Netherlands

• Synthetic Medical Records:
• Built a generative autoencoder (s2s LSTM) tool for synthesizing Electronic Health Records
• resulting in 0 waiting-time of confidential data acquiring for testing query pipeline
• Created generic to specific tunable results through tempered softmax in the outputs

Mar 2019 – May 2019 · 2 mos · Amsterdam, North Holland, Netherlands

• Course: Image Processing, Bachelor Artificial Intelligence, 2019
• Assisted in programming assignment creation and evaluation in MATLAB
• Provided personal guidance with a facetime of 8 hrs/week for the students

Aug 2017 – May 2018 · 9 mos · Chennai Area, India

• Embodied Cognition:
• Solely fabricated the perception guided grasping pipeline on the Moveit! stack of ROS as
• an atomic task, to build the behavior repertoire of the robot with a gripping arm

Sep 2016 – Aug 2017 · 11 mos · Chennai, Tamil Nadu, India

• Institute robotics team
• Qualified 13th among 34 global teams in the Intelligent Ground Vehicle Competition - IGVC 2017, Michigan USA
• Implemented the crucial navigation stack: localization through sensor fusion by Extended
• Kalman Filter (EKF), enabling obstacle-avoiding GPS waypoint navigation
• Designed and simulated the robot in Gazebo to test SLAM and lane-detection algorithms
• thus reducing manual testing times by 75%

May 2016 – Aug 2016 · 3 mos · Pune Area, India

• Co-authored Journal paper published in Soft Matter, RSC - 2017
• Simulated a Monte-Carlo Brownian dynamics to estimate the number of cubosomes (lipid
• nano-particles) adsorbed and corroborated with experimental droplet retraction times

Nov 2015 – Feb 2016 · 3 mos · Chennai Area, India

Jul 2014 – Feb 2015 · 7 mos · Chennai, Tamil Nadu, India