Tuhin Acharjee

Machine Learning & Computer Vision Engineer

Machine Learning and Computer Vision Engineer with 3.5+ years of experience building real-time video analytics, edge AI, robotic vision, face recognition, and Python backend systems. Skilled in NVIDIA DeepStream, TensorRT optimization, PyTorch deployment, Vision-Language Model fine-tuning, FastAPI, PostgreSQL/pgvector, Docker, and GPU profiling, with measurable gains in throughput, latency, GPU efficiency, and automation.

Work Experience

Computer Vision Engineer at Adagrad AI

November 2025 - Present

Designing and deploying real-time people analytics and edge AI pipelines for multi-camera deployments using NVIDIA DeepStream.

  • Designed and developed the complete real-time people analytics ML pipeline using NVIDIA DeepStream for two-camera edge-device deployments.
  • Developed people detection, tracking, entry/exit counting, gender classification, and age estimation workflows, achieving 96% accuracy in gender and age detection through a custom MiVOLO plugin for TensorRT-optimized PyTorch inference.
  • Built FastAPI backend services to receive ML engine payloads, process analytics data, and store operational events in PostgreSQL.
  • Implemented face recognition storage and retrieval using InsightFace embeddings, pgvector-based vector databases, and KNN similarity search, reducing search latency from 19 ms to 10 ms.
  • Implemented asynchronous inference support, increasing real-time multi-stream processing performance from 9 FPS to 25 FPS.
  • Developed rule-based computer vision algorithms for stalled vehicle detection, wrong-direction driving detection, and poor-visibility detection across blur, adverse weather, and visual degradations.
  • Fine-tuned VLM model using Supervised Fine-Tuning to detect road hazards including fallen objects, fire, and smoke from visual inputs.
  • Profiled inference workloads with NVIDIA Nsight Systems and Nsight Compute, reducing GPU stall time from 1150 ms to 1 ms through bottleneck analysis and optimization.
  • Developed InsightFace-based candidate verification, real-time seatbelt violation detection, and MediaPipe-based eye-gaze monitoring to track candidate attention and movement during driving tests.
  • Containerized and deployed ML services and backend components using Docker across edge-device workflows.

Software Development Engineer at Rosa Technology

March 2023 - October 2025

Built automated robotic rebar testing systems combining computer vision, machine learning, and robotic automation.

  • Designed and developed an automated robotic rebar testing system, improving operational efficiency by 60% over manual workflows.
  • Programmed robotic arm automation for pick-and-place operations and integrated automation logic for autonomous rebar handling during testing.
  • Developed CNN-based computer vision pipelines for rebar localization, elongation measurement, breakage detection, and quality assessment.
  • Implemented client-defined formula-based decision logic and integrated machine learning, computer vision, and automation components using Python, OpenCV, and TensorFlow.

Projects

Football Analysis System

End-to-end football analytics pipeline for automated player and ball tracking from broadcast video footage.

  • Developed an end-to-end football analytics pipeline for automated player and ball tracking from broadcast video footage.
  • Implemented YOLOv8-based real-time player and ball detection across video streams.
  • Built with Python, YOLOv8, OpenCV, K-Means clustering, and optical flow.