Anmol Varshney

Anmol Varshney

As a Mobility Engineer, I am driven by a strong ambition and determination to craft innovative solutions. My approach is deeply rooted in logic and insightfulness, allowing me to concentrate on ideal outcomes and meticulously engineer systems that are both effective and forward-thinking.

Open to

Bangalore · Hyderabad · Pune

Work style

hybrid, on-site

Identity verified by DigiLocker
Contact details — on requestProof of Work — on request

Experience

S

Mobility Engineer

SmartSoc India · Nov 2024 – Present

Not yet confirmed
  • Integrated AI/LLM models into edge devices on the iOS platform, enabling on-device intelligence, low-latency inference, and real-time processing without internet connectivity.
  • Successfully deployed and optimised Llama-based language models on iPhone devices, enabling fully offline AI experiences with efficient memory and resource utilization.
  • Enhanced LLM inference speed by 50% using Metal GPU acceleration and optimized tensor operations on over 10 iPhone models.
  • Improved system performance by implementing request batching, GPU-accelerated inference routing, and optimised API communication between device and backend.
  • Developed and integrated AI assistants capable of handling natural language queries, content generation, and contextual reasoning directly on-device.
  • Implemented model lifecycle management, including model download, caching, versioning, and runtime loading, ensuring reliable deployment and updates of AI models on iOS devices.
  • Contributed to the AI Copilot project by designing scalable AI architecture, integrating multiple AI models, and enabling seamless interaction between edge and cloud-based intelligence systems.
  • Improved on-device AI processing by integrating LLM models on iOS, supporting offline capabilities with 0% internet reliance.
V

Associate Software Developer

Valtech India · Aug 2022 – Nov 2024

Not yet confirmed
  • Built real-time AI-powered wall segmentation for iOS devices using AI model integration.
  • Enabled accurate segmentation of walls in both live video and static images.
  • Worked on an end-to-end image-processing pipeline including input validation, resizing, OpenCV decoding, mask filtering, and optimised data exchange with backend services.
  • Contributed to building preprocessing and post-processing pipelines to standardize model input/output.
  • Developed dynamic UI customization features for the V_Stream IOS OTT application.
  • Allowed immediate effect changes to the app design.
  • Ensured all components were generated dynamically within the app Allowed immediate effect changes to the app design.
  • Contributed to improving API response parsing, error handling, and fallback logic, ensuring that UI rendering remained stable.
  • Integrated the H&M website into a web-view within the mobile application.
  • Managed session handling to ensure a seamless and secure user experience.
  • Ensured smooth and efficient interaction between users and the H&M website through the mobile app.

Skills 0 proven through work

Also works with

Undo/Redo ImplementationLuminous Effect DesignSpatial Touch Point DetectionMetal API UsageAPI IntegrationRequirements AnalysisTeamworkTechnical TroubleshootingUser Interface DesignTime ManagementAlgorithm Design & OptimisationWork Planning and PrioritizationScalable System DesignTeam LeadershipProblem SolvingProject ExecutionUI Implementation from DesignOpenCV Library UsageAI Pipeline DevelopmentImage ProcessingComputer Vision ModelingPrompt EngineeringModel Fine-TuningModel QuantizationAPI Performance OptimizationApplication Performance OptimizationMachine Learning Model DeploymentLLM Application IntegrationJSON-Based Dynamic UI RenderingAI Solution ImplementationiOS Development

Proof of Work

Proof of Work

Anmol shares this with people who ask. You'll hear back either way.

Education

Master, Computer Application

SRM University Online · 2024 — 2026

Contact details

Contact details

Anmol shares this with people who ask. You'll hear back either way.

Ask about this candidate

AI responses may contain errors. Proof status and source information are provided by Proof of Skill.

A Proof CV — one profile, kept current, with the proof attached. Back to the portal