Animikh Aich 🚀

About Me

Machine Learning Engineer with 5+ years of experience in Applied Research and End-to-End Product Development. Expertise in scaling ML systems, leading cross-functional teams, and creating value by building novel applications in Computer Vision and deploying them efficiently in production environments.

Computer Vision & Machine Learning Engineer

  • Robotics: Autonomous Driving
  • Multi-Modal: Sensor Fusion
  • Generative AI: LLMs and Stable Diffusion
  • Object: Detection & Segmentation
  • Education: MS in AI
  • Experience: 5+ Years
  • Research: 130+ Citations
  • Labs: H2X Lab & BIT Lab

Tech Stack

With 3+ years of industry experience building scalable Computer Vision Products and 2+ years of academic research experience leveraging the latest advancements in the field, I have honed my skills in computer vision, machine learning, and cutting-edge research methodologies. Let's explore how my expertise can contribute to your projects and drive innovation.

Tools
Visual Studio Code Sublime Text Linux macOS Windows Google Chrome LaTeX Jupyter ChatGPT
Languages++
Python C++ JavaScript Dart Flutter Markdown HTML5 CSS3
Machine Learning & AI
PyTorch TensorFlow Keras OpenCV NumPy scikit-learn mlflow OpenAI Matplotlib
Web Development
Streamlit Flask FastAPI Nginx Replicate MongoDB
Cloud
AWS AWS S3 Azure Git Docker

Testimonials

Explore feedback from mentors, managers, professors, and colleagues regarding my abilities as a Machine Learning Engineer and Lead. These testimonials underscore my dedication, expertise, and professionalism, positioning me as an ideal candidate for any organization. They serve as proof of my readiness to excel in a corporate environment.

He independently comes up with brilliant solutions to challenging research problems, while always keeping up with recent advancements in AI and computer vision.

Eshed Ohn-Bar

Assistant Professor, Boston University

We were incredibly lucky to find and work with Animikh as a ML/AI intern this summer at Moultrie Mobile. We were able to accomplish multiple ML/AI goals this summer and are currently working on moving some of the features to production thanks to Animikh's efforts.

Robb Schiefer Jr

VP of Software Engineering - Moultrie, An EBSCO Company

‘Genuine expert’ is the phrase that pops into my mind when I think about Animikh. I have to say, I’ve never seen anyone handling multiple projects like him.

Aadil Srivastava

SDE 2, Amazon

Animikh defined his own research project within end-to-end autonomous driving systems and holistically tackled it, both in simulation and real-world settings. The defense for the project at the end of the MS thesis was outstanding.

Eshed Ohn-Bar

Assistant Professor, Boston University

I worked closely with Animikh, who was a Research Assistant in my lab this Spring. He demonstrated exceptional research, analysis, and development skills that greatly contributed to our projects.

Dokyun (DK) Lee

Associate Professor, Boston University

Animikh is one of the hardest-working people I have ever met, and I would describe his approach as smart hard work. Whenever something is assigned to him, rest assured it will be completed with utmost dedication.

Vinay Kumar Verma

Computer Vision Engineer 2, Stats Perform

Animikh is one of the most focused and driven people I've worked with. What sets him apart is his empathy and team spirit. He's a tech whiz, a great leader, and a fantastic coworker.

Dhairya Kumar

Machine Learning Engineer, Nintee

Animikh doesn't only know how to deliver, he knows how to deliver well. He has contributed greatly to Wobot's goal of automating and scaling AI processing.

Nitin Sharma

Product Manager 2, Wobot.ai

He has carried out several projects and has published papers under my guidance. Over the course of time, he has shown exceptional growth, dedication, and interest in Machine Learning.

Dr. Chetana Hegde

Lead Manager - Data Science, Fractal

He has got exceptional skills when it comes to coding and research. Animikh has been a great mentor for the Computer Vision (mid-level) Engineers and Interns.

Chirag Diwan

Operations Specialist, MongoDB

Projects

I learn by building! Allow me to introduce you to some of my fun projects, crafted over the years, often during my weekends. :-)

AI Wallpaper Generator

Wallpaper AI

Generate High Quality 4K Wallpapers from Simple Prompts.

  • Generative AI
  • Image Enhancement
  • Prompt Enhancement
  • NSFW Filtering
3D Text2LIVE

Autonomous Driving

End-to-end Conditional Imitation Learning in a Real-World model city.

  • PyTorch
  • Custom CNN
  • Imitaiton Learning
  • Safety-Critical Scenarios
3D Text2LIVE

3D Text2LIVE

Generate 3D renderings of an appearance edited object through text prompts.

  • 3D Vision
  • PyTorch
  • Generative AI
  • Neural Radiance Field (NeRF)
Box2D Reinforcement Learning

RL Racer

Double DQN-based racing agent trained using Reinforcement Learning.

  • PyTorch
  • OpenAI Gym
  • OpenCV
  • Deep Reinforcement Learning
Background Subtractor

Background Subtractor

FCN based Background Subtractor to extract unseen foreground objects.

  • Autoencoder
  • Tensorflow
  • Foreground Segmentation
  • Fully Convolutional Networks
Face Blur Algorithm

Face Blur

Real-time face blur algorithm using Intel OpenVINO Face Detection.

  • Intel OpenVINO
  • Face Detection
  • Gaussian Blur
  • Real Time Inference on CPU
Helmetless Rider Detection

Helmetless Rider Detector

YOLOv3 based object detection to capture Helmetless Riders and their License Plates.

  • Tensorflow
  • YOLOv3 Object Detection
  • Synthetic Data Generation
  • Single Shot Detector (SSD)
Human Segmentation

Human Segmentation

Fast lightweight semantic segmentation using autoencoder.

  • TensorFlow
  • OpenCV
  • Autoencoders
  • 10.3 µs Inference Time
Paper Architectures

Paper Implementation

Tensorflow 2.x Implementation of VGGNet and AlexNet Paper.

  • TensorFlow
  • Numpy
Tensorflow Training Utility

Training Utility

No-Code model training with quick architecture selection, deployed using Docker.

  • TensorFlow
  • Docker
  • Mixed Precision Training
  • No-Code Streamlit Interface
Face Recognition Dashboard

Face Finder

End-to-end application to find an uploaded face among a pool of images.

  • Face Recognition
  • MTCNN Face Detection
  • Flask
  • OpenCV

Resume

Research Experience

Graduate Research Assistant

Jan 2023 - Present

H2X Lab, Boston University, Boston, MA

  • Developed a real-world autonomous driving evaluation system using a Raspberry Pi-powered toy car, integrating RTSP for live video streaming and MQTT for control. Offloaded model inference to a server and constructed an indoor model city with lanes, traffic lights, and obstacles for testing.
  • Designed a novel offline evaluation metric by modeling prediction uncertainty, improving the correlation coefficient by 7.3% in both simulation and real-world performance for autonomous driving models.
  • Leveraged foundation models like Segment Anything and Depth Anything to transfer experiences from CARLA simulation to real-world autonomous driving, enhancing model performance in real-world scenarios by closing the Sim2Real gap.
  • Innovated model sampling techniques for multi-modal end-to-end Transformer-based imitation learning frameworks, incorporating test-time dropout and diverse backbones to train agents for CARLA evaluations.

Graduate Research Assistant

Feb 2023 - May 2023

BIT Lab, Boston University, Boston, MA

  • Developed rule-based multi-modal algorithm that leverages text prompts, image tags, and visual features to assist causal inference on user art study, enabling deeper analysis of user behavior and preferences.
  • Developed ViT and DINOv2-based models using PyTorch to identify AI-generated Deviant Art and achieved an accuracy of 92.04%.

Undergraduate Research Assistant

Feb 2018 - Jun 2019

RNS Institute of Technology, Bangalore, India

  • Authored 4 research papers with 100+ citations; performed comparative study in preprocessing techniques and algorithmic survey in sentiment analysis, forecasting, and encoding.

Education

MS - Artificial Intelligence

2022 - 2024

Boston University, Boston, MA, USA

Research Assistant: H2X Lab and BIT Lab

Courses: Robot Learning and Vision for Navigation, Computer Vision, Geometric Processing, Data Science Tools and Applications, Principles of Machine Learning, Artificial Intelligence.

BE - Electronics Engineering

2015 - 2019

Visvesvaraya Technological University, Bangalore, India

Project: Automatic Helmetless Rider Detection using Deep Learning

  • "Best Outgoing Student - 2019" among 180+ students
  • "First prize" in state competition at IIIT-Bangalore
  • "Letter of Appreciation" from the HoD, dept. of ECE

Professional Experience

Computer Vision & Machine Learning Engineer

Jun 2024 - Present

Moultrie - An EBSCO Company, Remote, USA

  • Building the Next Generation of Computer Vision Algorithms for Cellular Trail Cameras at Moultrie Mobile.

Machine Learning Engineer (Contractor)

Jun 2023 - Aug 2023

Moultrie - An EBSCO Company, Remote, USA

  • Experimented with and built algorithms for detection, segmentation, genearative AI, and 3D computer vision.
  • Confidential/sensitive information withdrawn.

Computer Vision Engineer & Lead

Jun 2019 - Jun 2022

Wobot Intelligence (Wobot.ai), New Delhi, India

  • Spearheaded a team of 14 engineers to develop over 90 real-time video analytics solutions scaled on Cloud using Kubernetes for 200+ concurrent CCTV cameras, resulting in increased hygiene compliance by 2x in the food and hospitality industry.
  • Enforced safety & hygiene compliance by developing multi-object detection & tracking, pose estimation, activity recognition, person re-identification, and face recognition algorithms, deployed across 3 continents reducing non-compliance by 25%+.
  • Applied classification, object detection & tracking algorithms like ResNet, Inception, EfficientNet, EfficientDet, YOLO, Centroid Tracking, and OpenCV Tracking to satisfy product requirements based on available compute resources.
  • Reduced data-to-production time by building development tools for data and models (using Python, Tensorflow, PyTorch & OpenCV) resulting in a 3x increase in productivity, positively impacting the team's efficiency and reducing time-to-market by 50%.
  • Implemented Synthetic Dataset Generation for object detection, reducing labeled data requirements by 35% and accelerating computer vision model development, resulting in significant cost savings and faster time-to-market.
  • Improved alert precision by up to 95% using ensemble models and temporal features reducing false positive alerts by 30%.

Contact

Thank you for visiting my website! I'm excited to hear from you. Whether you have questions, want to collaborate, or simply want to say hello, feel free to reach out to me through the email below.

Location

Boston, MA 02134

Phone

+1 (857) 260-0017