CV – Shanjidul Islam Sadhin

Education

• Bachelor of Science in Computer Science & Engineering
  • American International University-Bangladesh (AIUB)
  • January 2020 - December 2023
  • Distinction: Dean’s List Award (August 2023)

Work Experience

• Mid-AI Engineer (On-site)
  • Inument.com | April 2026 - Present
  • Engineered source-grounded LLM reasoning and evaluation, tying every candidate score to supporting evidence from interview transcripts.
  • Architected organization-level rubric and criteria configuration, raising evaluation transparency by 40%.
  • Owned self-serve organization onboarding end to end, replacing manual provisioning and increasing sign-ups by 70%.
  • Hardened onboarding against abuse with duplicate-account detection and 30-minute TTL verification tokens.
  • Built a self-serve Stripe billing system covering subscription tiers, one-time top-ups, and automated credit provisioning.
  • Integrated AppSumo marketplace distribution via webhook-driven provisioning and plan-tiered credit allocation.
  • Delivered GDPR and NYC Local Law 144 compliance for AI-driven hiring evaluation.
• Applied AI Engineer L2 (Remote)
  • Askturing.ai | June 2025 - March 2026
  • Led a cross-functional team delivering an automation-driven audit Q&A platform for 100+ active financial auditors.
  • Cut LLM token consumption by 41.6% — 208k to 104.5k per query — through adaptive chunking, dynamic context pruning, and query-aware retrieval ranking.
  • Migrated retrieval from OCR to Vision-Language Models with layout-aware embeddings, lifting citation-level accuracy from 62% to 88%.
  • Architected a tenant-isolated batch execution system on Dramatiq and Redis, running 300+ concurrent question jobs without starvation.
  • Built multi-agent retrieval orchestration in LangGraph with parallel RAG pipelines, semantic routing, and web-search fallback.
  • Engineered an event-driven automation framework over uploads, schedules, and email ingestion, raising onboarding completion by 30%.
  • Designed an approval and review system with authenticated multi-line comments and secure per-participant links.
  • Designed a continuous RAG evaluation and benchmarking framework measuring retrieval precision and answer quality.
• AI Engineer (On-site)
  • TechnyX.ai | December 2024 - May 2025
  • Designed and architected an AI system for image generation and virtual try-on.
  • Configured and optimized NVIDIA Triton Inference Server.
  • Led development of advanced computer vision and multimodal AI solutions.
  • Architected and deployed vision-language models for in-house API development.
• Freelancer (Remote)
  • UpWork | October 2024
  • Developed a state-of-the-art super-resolution model for image up-scaling.
  • Modified the architecture of the “Dual Attention Transformer”.
  • Designed a robust architecture that utilizes channel-wise concatenation.
• Junior AI Developer (Remote)
  • CRTVAI | April 2024 - September 2024
  • Designed and implemented system architecture and API endpoints for automated quality control.
  • Fine-tuned speech-to-text models, deploying server-less models.
  • Improved the Voice Activity Detection pipeline.
  • Achieved a 25% reduction in GPT API calling costs.
• Research Assistant (On-site)
  • Computer Vision and Bio-Robotics | Sep 2023 - Jan 2024
  • Contributed to the creation of a research dataset containing 12,000+ labeled images.
  • Reduced research time by 20% by implementing efficient data analysis.

Skills

• Languages: Python, C++, C#, JavaScript, PHP, SQL
• Libraries: Pytorch, TensorFlow, Keras, NumPy, Pandas, Scikit-Learn, OpenCV, YOLO
• Frameworks: FastAPI, LangChain, Flask, Django
• Tools: GIT, DVC, MLflow, DagsHub, MySQL, PostgreSQL, ChromaDB, FAISS
• Platforms: Linux, Windows, Docker
• Cloud-Platforms: AWS, vLLM
• Soft Skills: Leadership, Writing, Public Speaking, Time Management

Publications

• Speech Emotion Recognition using Transfer Learning Approach and Real-Time Evaluation in English and Bengali Language Pre-Print · 2023 Shanjidul Islam Sadhin. (2023). "Speech Emotion Recognition..." Pre-Print.

Talks

• Importance of data, and need for data in good quality research for computer vision Talk · 2024

Teaching

• Teaching experience 2 Workshop · University 1, Department · 2015
• Teaching experience 1 Undergraduate course · University 1, Department · 2014

Service and Leadership

• Problem Solving: Solved 800+ problems in different Online Judges.
• 12th National Undergraduate Mathematics Olympiad 2021: Participated (Dhaka North Region).
• Hacktoberfest-2023: Contributed to Refactoring and Programming Solutions.