Sai Dileep Munugoti

Software Engineer

Bengaluru, Karnataka, India8 yrs 10 mos experience

Most Likely To SwitchHighly Stable

Key Highlights

Achieved 93% accuracy in breast cancer scoring AI solution.
Developed innovative RNN models with published research.
Expertise in Machine Learning and Deep Learning applications.

Stackforce AI infers this person is a Quantitative Developer with expertise in Machine Learning and Healthcare applications.

Contact

Skills

Core Skills

Machine LearningDeep LearningComputer VisionTheoretical Machine Learning

Other Skills

CPythonRecurrent Neural NetworksPowerPointMatlabNI MultisimLaTeXC++R

About

I am currently working as a quant developer in a hedge fund. I am a graduate in Electrical and Electronics Engineering from IIT Guwahati with a minor in Mathematics.

Experience

8 yrs 10 mos

Total Experience

2 yrs 11 mos

Average Tenure

6 yrs 9 mos

Current Experience

Kivi capital

Quantitative Developer

Aug 2019 – Present · 6 yrs 9 mos · Gurgaon, Haryana, India

CPythonMachine LearningDeep Learning

Soroco

Software Developer

Sep 2018 – Aug 2019 · 11 mos · Bangalore

Qualcomm

Associate Software Engineer, Audio DSP

Jul 2017 – Sep 2018 · 1 yr 2 mos · Bengaluru Area, India

Iit guwahati

Winner, HER2 Scoring Contest | Deep Learning for health care

May 2016 – Jul 2016 · 2 mos · Guwahati Area, India

Developed an end-to-end AI solution for predicting/scoring breast cancer in whole-slide-images. I was responsible for CNN pipeline which attained 93% accuracy and was the state-of-the-art for HER2 scoring in IHC. This pipeline is the only one which was able to out perform human pathologists in HER2+ breast cancer scoring. We also presented our algorithms and results at Nottingham Pathology 2016.

Deep LearningComputer Vision

Iiit hyderabad

Summer Research Associate | Theoretical Machine Learning

May 2015 – Jul 2015 · 2 mos · Hyderabad Area, India

Worked on the development of two new kinds of Recurrent Neural network (RNN) models and also provided their theoretical proofs. Both these RNN’s ares tudied from an associative memory point of view and are based on Hopfield Neural Network. This work got published in IJCNN 2016 and ICONIP 2015

Recurrent Neural NetworksTheoretical Machine Learning