Skip to content

AI Systems Engineer • Agentic AI • Edge/Video AI • ML Infrastructure

I build production-grade AI systems that connect models, infrastructure, and business workflows.

Machine Learning Engineer focused on agentic AI systems, Video-RAG, real-time edge inference, MLOps, and client-facing AI delivery across safety-critical and enterprise environments.

Open to AI/ML, GenAI, ML Systems, Computer Vision, Edge AI, MLOps, and Applied AI Consulting roles.
View Case Studies Get in Touch

Proof of impact

45%
reduction in manual monitoring
30 FPS
real-time video analytics on NVIDIA Jetson AGX
2x
inference throughput improvement
60%
latency reduction
50%
lower data acquisition costs through synthetic data
30%
faster deployment workflows

Featured work

Selected case studies

Agentic AI + Edge AI + Computer Vision

Production Edge Agentic AI for Mining Safety

Designed real-time on-device agentic AI systems for safety-critical video analytics on NVIDIA Jetson AGX.

  • 45% reduction in manual monitoring
  • 30 FPS real-time video analytics
  • Improved safety monitoring reliability
Agentic AIComputer VisionNVIDIA JetsonTensorRTCUDA
Read case study

Multimodal RAG + LLM Systems

Video-RAG for Continuous Video Search

Architected retrieval-oriented video understanding pipelines for natural-language search over live and long-horizon video streams.

  • Sub-second search latency over multi-day indexed video
  • Contextual querying and decision support over live video streams
  • Improved explainability through retrieval-backed reasoning
Video-RAGMultimodal RetrievalCLIPVLMsLLMs
Read case study

Agentic AI + Enterprise Workflow Automation

Enterprise AI for Sprint Planning and Resource Allocation

Developed an agentic planning workflow to support prioritization, sequencing, trade-off analysis, and resource allocation.

  • Improved visibility into dependencies and constraints
  • Supported AI-assisted prioritization and sequencing
  • Framed as a human-AI collaboration system for workflow redesign
Agentic AIEnterprise AIWorkflow AutomationHuman-AI CollaborationProduct Ops
Read case study

ML Systems + Inference Optimization

High-Performance Inference and MLOps for Real-Time AI

Built GPU-accelerated inference and deployment pipelines that improved throughput, latency, reproducibility, and validation.

  • 2x throughput improvement
  • 60% latency reduction
  • 50% IPC latency reduction
TensorRTONNXCUDAGStreamerMLflow
Read case study

Experience

Where I've shipped AI systems

  1. Machine Learning Research Engineer · JSquared Technologies

    May 2024 – Present

    Production AI systems for safety-critical mining and operational workflows

    Led development and deployment of real-time AI, agentic AI, Video-RAG, and edge inference systems for mining safety and workflow automation.

    Agentic AIVideo-RAGEdge AIComputer VisionTensorRTCUDAGStreamerMLflowAWSDockerMLOps

  2. Machine Learning Engineer · Sapiient Advanced Technologies

    Aug 2022 – Feb 2023

    Real-time ML and anomaly detection for infrastructure inspection

    Built optimized anomaly detection and video-based analytics systems for infrastructure inspection.

    Anomaly DetectionComputer VisionReal-Time MLDashboardsXGBoostLightGBM

  3. Software Development Engineer · TechNomads

    Jan 2022 – Jul 2022

    Backend, cloud, and API engineering

    Built scalable REST APIs and AWS-based platform features for real-time analytics workflows.

    BackendREST APIsAWSCloudProduct Engineering

Skills

Grouped by what you're hiring for

AI / ML / GenAI

For AI/ML and GenAI hiring managers

Machine LearningDeep LearningLLMsRAGAgentic AINLPComputer VisionAnomaly DetectionSynthetic DataResponsible AIPrompt EngineeringTool Calling

LLM, RAG & Serving

For GenAI / Agentic AI & inference teams

LangChainLangGraphMultimodal RetrievalVideo-RAGLLM-powered AutomationvLLMTensorRT-LLMONNX RuntimeTensorRTCUDAReal-Time InferenceBatch InferenceLatency Optimization

ML Modeling & Validation

For applied ML and model-quality roles

PyTorchTensorFlowScikit-learnXGBoostLightGBMFeature EngineeringKnowledge DistillationModel EvaluationDrift MonitoringPerformance TestingBias/Error Analysis

Infrastructure & MLOps

For MLOps / platform engineering teams

MLflowCI/CDExperiment TrackingModel DeploymentMonitoringAWS EC2AWS SageMakerAWS BedrockSQLSparkKafkaREST APIsDockerGitLinux

Systems & Edge

For edge AI and performance engineering

NVIDIA JetsonHailoGStreamerFP16QuantizationEdge-device RunnersHardware-in-the-loop ValidationGPU-accelerated Decoding/Encoding

Consulting & Delivery

For forward-deployed / applied AI consulting

Stakeholder ManagementClient-Facing CommunicationRequirements GatheringSolution DesignBusiness Process AnalysisAgile DeliveryProduct PrototypingTechnical DocumentationExecutive CommunicationCross-Functional Execution

Research & writing

Where I go deep

Human–AI Collaboration & Workflow Redesign

How agentic systems augment human decision-making in planning, prioritization, and resource allocation.

Enterprise AI for Sprint Planning

Continuous & Multimodal Video Retrieval

Retrieval-oriented video understanding for natural-language search over live and long-horizon streams.

Video-RAG for Continuous Video Search

Edge AI for Safety-Critical Systems

Reliable on-device perception–decision–action loops under strict latency, power, and compute limits.

Production Edge Agentic AI for Mining Safety

Contact

Interested in AI systems, agentic AI, edge AI, or ML infrastructure roles? Let’s connect.

Open to AI/ML, GenAI, ML Systems, Computer Vision, Edge AI, MLOps, and Applied AI Consulting roles.

Email viradiyapreet@gmail.com GitHub github.com/pinakin7 LinkedIn LinkedIn profile