From production APIs to industrial research. Each case connects my contribution to its evidence.
First author and system researcher
96.2% mutant-level exact-match
Designed the report-validation workflow and evaluated deterministic and model-assisted checking.
Co-author and retrieval researcher
65.8% Precision@1
Co-authored evaluation of local retrieval representations and fusion for construction drawing sets.
First author and doctoral researcher
94.5% mean balanced accuracy
Analyzed joystick-mounted inertial measurements and separate gaze measures to study experience-related behavior.
Co-author and benchmark researcher
Co-authored evaluation of information extraction, sheet references, and cross-discipline coordination.
Co-author and multimodal research contributor
87.87% weighted F1, zero-shot GPT-4o
Co-authored a comparison of zero-shot and fine-tuned models for construction locomotion prediction.
First author and prototype researcher
94.3% reported classification accuracy
Integrated local scene captioning, voice input, recent locomotion history, and human clarification.
Prompt Engineer (Project-based), July 2023 to January 2024
Built and integrated multi-agent workflows, image-based features, and retrieval-augmented generation.
AI/NLP Engineer, Headless Technologies, December 2022 to January 2024
Collected and annotated data, trained and tuned the classifier, and built backend services and APIs.
Personal project developer
Developed image-generation projects using generative adversarial networks.
AI/NLP Engineer, Headless Technologies, December 2022 to January 2024
Developed and deployed Rasa and Dialogflow chatbots, natural-language understanding, dialogue management, backend services, and APIs.
Doctoral researcher, proposed trainer evaluation
Design a session-end workflow for behavioral analysis, reference retrieval, feedback drafting, and verification.
First author and literature-review researcher
Synthesized application areas and architectural gaps, emphasizing retrieval, calculations, and human review.
Energy Assessment Team Leader & Researcher, September 2024 to present
Lead assessments, analyze utility bills and on-site measurements, perform energy balances, and author client technical reports.
AI/NLP Engineer, Headless Technologies, December 2022 to January 2024
Curated and validated data, fine-tuned NLP models, and built backend services and APIs.
Doctoral researcher and pipeline contributor
Organize simulator, video, gaze, digital joystick, and inertial streams for inspectable research analysis.
Personal project developer
Trained a Bengali contextual question-answering model and published project code.
Prompt Engineer (Remote, Project-based), March to May 2023
Defined a project roadmap, analyzed requirements, designed the system, and built an initial demonstration.
Personal project developer
Developed a contextual retrieval model that ranks supplied passages for a question.
Prototype developer
Built a task-editable video monitoring workflow with event timestamps and evidence clips.
Co-author and assessment researcher
Contributed to temporal behavior analysis and evidence-linked operator assessment reports.
First author and system researcher
Developed a utility-bill extraction and review workflow for energy assessments.
Doctoral researcher, planned study
Design an evaluation of phase identification, behavioral interpretation, and propagation of upstream errors.
LSU Industrial Training & Assessment Center · September 2024 to present
I lead industrial energy assessments: utility-bill analysis, on-site measurement, energy-balance calculations, and client technical reports. Totals are team assessment outcomes.
Recommended annual electricity savings
8,208,899 kWh/year
16 assessments with recommendations
Implemented annual electricity savings
5,950,754 kWh/year
11 assessments with implementation reports
AI engineering roles where systems meet real operations.