Sep 2018 – Jul 2019 · 10 mos · Atlanta, Georgia, USA

• Advised by Prof. Dhruv Batra and Prof. Devi Parikh. Performing research in the areas of machine learning, reinforcement learning, computer vision, and natural language processing. Developed models for generating navigational instructions for navigational trajectories in Matterport3D (a photo-realistic 3D indoor environment). Developed a hard-attention model, trained via gumbel-softmax straight through estimator. Published at CVPR 2019 (see Publications).
• Currently fine-tuning instruction generation using reinforcement learning methods such as self-critical sequence training and actor-critic.

Nov 2017 – Jul 2018 · 8 mos · Greater Bengaluru Area

• Advised by Prof. Ambedkar Dukkipati. Developed a decoder-less variant of Skip-Thought Vectors (maps natural language sentences to vectors ) which trained 10 times faster. Worked on generative adversarial networks (GANs) for semi-supervised learning. Developed models that explicitly learned to generate functions which in turn access a knowledge base (KB) for answering questions.

Jun 2016 – Nov 2017 · 1 yr 5 mos · Greater Bengaluru Area

• Led a team which used recurrent neural networks (RNNs) to automatically find easy-to-automate business processes (for e.g. payroll management, settling vendor disputes for top e-commerce websites).
• Designed and implemented a patent-pending work queue-based distributed systems framework operational at Fortune 500 companies. The framework allowed developing efficient and fault-tolerant automation systems with minimal internal state.

May 2015 – Jul 2015 · 2 mos · Menlo Park, California · On-site

• Worked with the configuration management team in the Core Engineering Group. Found and fixed bottlenecks in existing architecture. Parallelized configuration checking service by splitting into master and slaves, speeding it up by 1000 times.

Aug 2013 – Jan 2014 · 5 mos · Kharagpur Area, India

• Developed and implemented fast customized algorithms for gesture recognition and integrated them with Windows OS for a smooth experience of playing video games, delivering powerpoint presentations and much more just by hand gestures.