Archit Mangrulkar

Software Engineer

Indore, Madhya Pradesh, India4 yrs 10 mos experience
Most Likely To SwitchAI Enabled

Key Highlights

  • Expert in AI-driven video stabilization technologies.
  • Led commercialization of advanced camera solutions for smartphones.
  • Published research on NLP and computer vision applications.
Stackforce AI infers this person is a Computer Vision and AI Specialist in Consumer Electronics.

Contact

LinkedIn

Skills

Core Skills

Computer VisionSoftware DevelopmentProduct ManagementMachine LearningEmbedded Systems

Other Skills

3D VisualizationAIAgile & Waterfall MethodologiesAlgorithm DesignAlgorithmic TradingAlgorithmsAnalytical SkillsApplication Programming Interfaces (API)CC++CommunicationComputer ScienceConfluenceData AnalysisData Analytics

About

Innovative Software Engineer | AI & Computer Vision Specialist | Camera Technology Expert Current Role Software Engineer at Samsung Research, specializing in enhancing user experience through cutting-edge computer vision and AI solutions. Key contributions include developing real-time video stabilization technologies like VDIS, Hyperlapse, and Super Slow Motion for flagship and mid-range Samsung smartphones globally. Core Expertise - Camera Technologies: Extensive experience with camera pipelines (LSI, MTK, Qualcomm) and sensors from Sony, OmniVision, and Onsemi - Video Stabilization & Hyperlapse: Advanced algorithms for stabilization using gyroscopic sensors, accelerometers, and AI - Super Slow Motion: Expertise in high frame-rate capture, image processing, and CNN-based optimization - Software Development: Proficient in SDLC, Agile, CI/CD tools, and version control systems - Programming: Skilled in C++, Assembly, OpenCV, and algorithm optimization for robust and scalable solutions Research & Academia - NLP and Computer Vision: Research experience in stance and premise classification, with a published paper at SMM4H (COLING 2022) on COVID-19 Twitter dataset analysis. -3D Human Pose Estimation: MITACS'23 internship at the University of Alberta, leveraging 3D transformers and attention-based methods for point cloud reconstruction. - Hardware and Deep Learning: Research at TU Dresden designing C++-based approximate multipliers for TensorFlow Lite. - Additional Projects: Experience in Image Segmentation, Style Transfer, and multimodal learning. Education B.Tech in Computer Science from the Indian Institute of Technology (IIT) Kharagpur. Achievements - Over 1 year of industry experience and 3+ years in academic research. - Expertise in advanced QA systems, domain adaptation, and performance optimization. Passion for Innovation Driven to push boundaries in computer vision, NLP, and multimodal learning. Open to collaboration and discussions to shape the future of technology.

Experience

4 yrs 10 mos
Total Experience
10 mos
Average Tenure
1 yr 11 mos
Current Experience

Samsung r&d institute india

Advanced Developer

Jul 2024 – Present · 1 yr 11 mos · Bangalore Urban, Karnataka, India · On-site

  • Working in the Visual Quality Solutions part under Camera Solutions Group in Visual Intelligence team, responsible for developing real-time Video + Image Quality solutions for key features like Night Mode, HDR10, VIDS, Hyperlapse, Super SlowMo
  • Full Ownership of Video Stabilization Features: Spearheaded the design, development, and optimization of Video Stabilization, QuickTake, Hyperlapse, and Astrolapse on LSI and MTK chipset pipelines
  • Product Commercialization: Successfully led commercialization of video solutions for Samsung’s S (flagship) & A/M/F (innovative) series smartphones targeted at NA, EUR, and Asian markets, ensuring alignment with key performance indicators, technical fitness, and operational reviews
  • Flagship Device Feature Rollout: Directed the solution bring-up process, feature propagation, and OS upgrades for flagship and innovative devices, including M56, A56, and S23, while maintaining seamless integration and high performance
  • AI-Driven Video Stabilization: Evaluated AI-based video stabilization solutions incorporating camera metadata like OIS and Gyro dumps for advanced post-processing and enhanced video stabilization
  • Currently developing video denoising & portrait to landscape video solutions for commercialization in flagship segment [Flip, Fold & S series]
  • Conducted 34 hours of Advanced C++ & OpenCV sessions as part of LnD training for a pax of 120+ engineers across Visual Intelligence, XR, Network modem, Voice Intelligence, Ad & Services PF, SmartThings teams
C++OpenCVAIVideo StabilizationImage Quality SolutionsComputer Vision+1

Quant club, iit kharagpur

3 roles

Advisor

Aug 2023 – May 2024 · 9 mos

Data Head

Aug 2022 – Jul 2023 · 11 mos

Associate Quant Researcher

Jun 2021 – Jul 2022 · 1 yr 1 mo

University of alberta

Research Intern

May 2023 – Aug 2023 · 3 mos · Edmonton, Alberta, Canada · On-site

  • Worked on the Multimodal Motion Capture project under Prof. Li Cheng of Vision & Learning Lab, Department of Electrical and Computer Engineering, University of Alberta
  • Developed large-scale multimodal dataset of humans in the wild of RGBD images, eye-tracking information, speech data
  • Programmed a multithreaded C++ server and Python GUI client using PyQt5 to achieve concurrent image capture
  • Designed a 3D human pose tracking & clustering module for multi-view images with YOLOv5, DeepSORT, & DBSCAN
C++PythonYOLOv5DeepSORTComputer VisionMachine Learning

Technische universität dresden

Research Intern

May 2022 – Aug 2022 · 3 mos · Dresden, Saxony, Germany · On-site

  • Working on Cross-Layer Approximation for Embedded Machine Learning under the Chair of Processor Design at the Centre for Advancing Electronics Design (cfaed)
  • Designed neural operators as C static libraries for fast 8-bit FPGA inference of neural networks using TensorFlow Lite
  • Explored cross-layer granularity combining signed 8-bit lookup tables, polynomial regression & EvoApproxLib multipliers
  • Reduced inference time by 2x using OpenMP’s multithreading, autovectorization, compiler flags & cache optimizations
CTensorFlow LiteOpenMPEmbedded SystemsMachine Learning

Kharagpur data analytics group

Student Member

Aug 2021 – Jul 2022 · 11 mos · Kharagpur, West Bengal, India

Education

Indian Institute of Technology, Kharagpur

B. Tech — Computer Science & Engineering

Nov 2020 – Apr 2024

Choithram School North Campus - India

Apr 2009 – Mar 2018

Stackforce found 100+ more professionals with Computer Vision & Software Development

Explore similar profiles based on matching skills and experience

Zlatina Stoeva

Zlatina Stoeva

Head of Talent Operations

at Xogito Group, Inc

Bulgaria12 yrs 4 mos exp
Talent ManagementRemote WorkRecruitingHuman ResourcesInternal Mobility
Viveck P Kumar

Viveck P Kumar

Chief Product Officer

at Sleek

Singapore, Singapore21 yrs 3 mos exp
Product ManagementGlobal Product ManagementProduct StrategyTeam ManagementProduct Marketing
Ravinder Singh Mahori

Ravinder Singh Mahori

Principal Engineer

at Infineon Technologies

Bengaluru, India15 yrs 3 mos exp
BluetoothEmbedded SystemsBluetooth Low EnergyProduct LeadershipTechnology Management
VH

Volker Hilsheimer

Chief Maintainer of the Qt Project

at Qt Project

Norway27 yrs 1 mo exp
Divyansh Shukla

Divyansh Shukla

Founder

at NovaX AI

Lucknow, India6 mos exp
Artificial IntelligenceMachine LearningConversational AICloud Computing
Nikhil Betke

Nikhil Betke

Full Stack Developer

at UBS

Pune, India5 yrs 10 mos exp
Back-End Web DevelopmentDatabase DevelopmentMicroservicesJava DevelopmentFront-End Web Development
Katta Sivasai

Katta Sivasai

Software Engineer G8

at Cisco

Bengaluru, India6 yrs 9 mos exp
NetworkingEngineering
Noureen Nasar

Noureen Nasar

Associate Software Engineer (Data Engineer)

at Epsilon India

Bengaluru, India2 yrs 10 mos exp
Machine LearningData Engineering