SIGN UPLOG IN
Find MentorsFind FreelancersHow It Works
SIGN UP
LOG IN
Kuldeep Singh Sidhu

Kuldeep Singh Sidhu

Mentor
5.0
(52 reviews)
US$35.00
For every 15 mins
120
Sessions/Jobs
ABOUT ME
Experienced Machine Learning Engineer | Top 2% on StackOverflow
Experienced Machine Learning Engineer | Top 2% on StackOverflow

Experienced Research And Development Engineer with demonstrated experience in building scalable Machine Learning Systems, Deep Learning, Natural Language Processing and Full stack development.

I breathe, eat and live software development. I've built software solutions ranging from TIc-Tac-Toe AI using reinforcement learning to web applications serving the top tiers of web traffic. Let me find the solution to your problems too.

I am also a mentor, I love teaching programming, especially programming with Python. I am ranked top 5% on Stack Overflow for answering Python, top 2% overall. I love figuring out how someone sees their world, their problems, and then help fill in the gaps. To contribute back to the community I have published open-source packages with over 10k downloads. Through mentoring, I accelerate my own constant learning, because there is always something that you want to do better when teaching that knowledge to others!

I see programming as an art. Code is expression. It needs to have clarity, purpose, elegance and efficiency to communicate well, to execute well. As a result, I produce software of the highest quality, not only functional and tested, but highly readable for future maintainers.

Hindi, English
New Delhi (+05:30)
Joined November 2020
EXPERTISE
Python
8 years experience | 2 endorsements
Keras
5 years experience
TensorFlow
4 years experience | 1 endorsement
Deep Learning
3 years experience | 1 endorsement
Apache Spark
1 year experience
Google Cloud Platform
1 year experience | 1 endorsement

REVIEWS FROM CLIENTS

5.0
(52 reviews)
Aravind Sanjeevi
Aravind Sanjeevi
October 2021
Kuldeep has explained a lot of things and he makes sure that its understandable.
Lililashka XX
Lililashka XX
October 2021
Kuldeep helps me set up python in virtual environment in Mac M1. The system works perfectly!
Lililashka XX
Lililashka XX
October 2021
Highly recommended. I will definitely work with Kuldeep again. His work is exceeding expectation and timely.
Stephanie Laface
Stephanie Laface
September 2021
Machine learning expert, helped me debug my code very quickly.
James R
James R
August 2021
Very condescending, had to practically beg the mentor to fully complete the agree upon freelance. I had to repeat myself on numerous occasions on multiple talking points. As an adult, I don't appreciate being interrupted and told to 'chill out'
Mike G
Mike G
August 2021
I'm brand new to ML but have an upcoming project that requires it. Kuldeep has a way of explaining things that makes even the most complex systems seem simple. Definitely appreciated his patience. Thank you!
Michael
Michael
August 2021
Great explanation, patient
Lililashka XX
Lililashka XX
August 2021
Fast turn around, clear communication, reliable and have patience! Highly recommended.
Julio Anthony Leonard
Julio Anthony Leonard
August 2021
Thanks, kuldeep solve my problem patiently. Awesome mentor
MEC
MEC
August 2021
amazing tutor! Everything was explained super well
SOCIAL PRESENCE
GitHub
2D-Navier-Stokes-Solver
As the field of Computational Fluid Dynamics (CFD) progresses, the fluid flows are more and more analysed by using simulations with the help of high speed computers. In order to solve and analyse these fluid flows we require intensive simulation involving mathematical equations which governs the fluid flow, these are Navier Stokes (NS) equation. Solving these equations has become a necessity as almost every problem which is related to fluid flow analysis call for solving of Navier Stokes equation. These NS equations are partial differential equations so different numerical methods are used to solve these equations. Solving these partial differential equations so different numerical methods requires large amount of computing power and huge amount of memory is in play. Only practical feasible way to solve these equation is write a parallel program to solve them, which can then be run on powerful hardware capable of parallel processing to get the desired results High speed supercomputer will provide us very good performance in terms of reduction in execution time. In paper focus will be on finite volume as a numerical method. We will also see what GPGPU (General-Purpose computing on Graphics Processing Units) is and how we are taking its advantages to solve CFD problems.
C
19
10
Youtube-Views-Hack
Increase Youtube Views with multiple videos playing at once and reloading at a set frequency
HTML
17
21
Stack Overflow
3571 Reputation
2
9
20
EMPLOYMENTS
Senior Data Scientist
Lowes
2020-10-01-Present

Working on understanding 2 billion+ search queries made by our Lowe's customers on the digital platforms to personalize/recommend...

Working on understanding 2 billion+ search queries made by our Lowe's customers on the digital platforms to personalize/recommend 5 million+ products and impact our 100 billion USD revenue annually.

• Created a Query Classification model for multi-class classification using TensorFlow, PySpark, TensorFlow Serving(TFX) & FastAPI with low latency throughput to be used in search ranking.
• Trained a domain-specific BERT to have an accurate & efficient representation of queries and documents related to the home-improvement domain on over 20 million open-source (Semantic Web 2020, Amazon 2018, etc) & in-house data points. The language model outperforms distilled BERT with 20% fewer parameters improving latency.
• Conceptualised and built a behavioural tagging model that maps attributes between products and user queries for the top most business-driving queries by mining relationships over millions of data points using PySpark.
• Worked on improving Elasticsearch query for better information retrieval & ranking using Bayesian optimization
• Worked on enriching our Elastic Index with user behaviour signals resulting in 16% better recall
• Created a 1000 times faster lexical matcher based on SymSpell to compute the importance of each token in a user query for over 3 million + unigrams and bigrams

Skills: Recommendation Systems, Natural Language Processing, Information retrieval, Deep Learning, System design
Technologies: Tensorflow, PyTorch, Transformers, BERT, Pandas, Elasticsearch, PySpark, ONNX, TF-serve, FastAPI

Python
View more
Python
View more