Skip to content
View Thush099's full-sized avatar

Block or report Thush099

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Thush099/README.md

Thushanth Mahendran — AI & Data Science

LinkedIn Email Repositories


About Me

  • Education: BSc (Hons) Artificial Intelligence & Data Science undergraduate at IIT Sri Lanka (affiliated with Robert Gordon University)
  • Industry Experience: Former AI Engineering Intern at DecodeLabs — delivered end-to-end applied ML, NLP recommender, guardrail, and OpenCV/OCR pipelines
  • Engineering Focus: Multimodal OCR forensics & claim auditing, adversarial tool-agent evaluation, hybrid retrieval (RAG, FActScore NLI, G-Eval), streaming ML observability, and open-source ML tooling

Live GitHub Activity & Language Distribution

Thushanth Mahendran GitHub Activity, Streaks, and Languages


Featured Systems & Benchmarks

veridoc-forensics — Multimodal OCR & Claim Verification traceguard-eval — Adversarial Agent Evaluation

CM3604_CW — FActScore NLI DecodeLabs-Internship — Applied AI

domain-ai — Task Priority ML CM2604-Churn-Classifier

View Detailed Methodology & Verified Metrics
Repository Scope & Engineering Details Verified Results & Highlights
veridoc-forensics Multimodal document auditor combining OpenCV skew/blur restoration, JPEG Q90 ELA + MAD noise tamper heatmaps, Tesseract OCR, hybrid BM25/TF-IDF claim verification, and FastAPI Studio UI Restores degraded OCR char accuracy from 0.0% → 99.7% (66.7% → 99.9% mean across suite), 100.0% claim verdict & tamper accuracy, 16 passing pytest tests
traceguard-eval Deterministic multi-step tool-agent sandbox, adversarial prompt-injection & HTTP/JSON fault fuzzer, schema/budget guards, and FastAPI Trace Replay UI TraceGuardHardenedAgent scores 100.00 vs 63.33 (SchemaRetryAgent) & 39.58 (NaiveAgent) on benchmark (100.00 vs 61.00 vs 37.69 on 30-run fuzz); 17 passing pytest tests
CM3604_CW Automated fact-checking of LLM outputs against BM25 evidence passages with grouped CV ablations & error analysis Majority baseline 50.68% (112/221) → Lexical overlap 84.16% (186/221) → Fine-tuned DeBERTa NLI 88.24% (195/221)
DecodeLabs-Internship Four applied AI capstones spanning input guardrails, customer classification, TF-IDF skill-gap recommendations, and document OCR Combines OpenCV perspective/contrast normalization with Tesseract extraction across end-to-end runnable modules
seniruvitharanage/domain-ai Contributed priority-scoring ML sub-pipeline merging TF-IDF developer issue text with repository & workflow metadata Gradient Boosting model trained on 9,120 samples achieving 96.97% accuracy & weighted F1 on 2,280 test cases
CM2604-Churn-Classifier Telco customer churn prediction comparing hyperparameter-tuned Decision Tree and Dropout/EarlyStopping Keras MLP Strict train-only SMOTE oversampling to prevent data leakage under ROC-AUC and generalization-gap evaluation

Open-Source Contributions & Enhanced Forks

Repository Upstream Project Engineering Contributions & Verification
Thush099/chonkie feyninc/chonkie Fixed OverlapRefinery._split_text & _recursive_overlap infinite-loop / whitespace chunk boundary bugs (fix/overlap-refinery-recursive-whitespace, upstream #681); 89 refinery & recursive chunker tests pass (4 from_recipe tests deselected without huggingface_hub)
Thush099/cleanlab cleanlab/cleanlab Fixed IndexError bounds ordering in token_classification.rank.issues_from_scores (upstream #1338) and single-class K == 1 ValueError in rank.get_normalized_margin_for_each_label (upstream #1356) on fix/rank-boundary-guards; 124 upstream/regression tests pass across rank, token classification, util & validation modules
Thush099/hiring-agent interviewstreet/hiring-agent Resolved scoring clamping, JSON extraction & defensive transform bugs and built calibration_audit.py for offline rubric integrity (100.0% tier accuracy, 97.2% evidence grounding) and counterfactual fairness auditing (0.00 delta, 1.000 Kendall's τ) on feat/offline-rubric-calibration-audit; 13 passing tests

ML & LLM Engineering Toolkit

A suite of standalone, modular Python packages covering retrieval, LLM faithfulness, production drift monitoring, differential privacy, causal inference, and multimodal attention — each shipped with runnable CLIs and automated pytest suites.

LLM Systems & Evaluation
  • rag-pipeline
    Okapi BM25 + L2-normalized dense cosine retrieval, Reciprocal Rank Fusion (k=60), cross-encoder proximity re-ranking, and sentence-level [doc_id] citation grounding.
  • llm-eval-harness
    Atomic claim decomposition with numeric/negation contradiction detection, rubric G-Eval scoring, and JSON/Markdown multi-model leaderboards.
ML Observability & Drift Monitoring
  • drift-detector
    Streaming concept-drift detection via Hoeffding-bound ADWIN and two-sided Page-Hinkley tests paired with adaptive SGDRegressor retraining.
  • drift-tracker
    Batch feature, prediction, and data-quality observability across PSI, two-sample KS, Jensen-Shannon divergence, unseen category detection, and schema contracts.
Data Contracts & Federated Privacy
  • data-profiler
    Semantic column inference (5 types), IQR/z-score outlier & leakage audits, declarative schema validation, and prioritized dataset remediation plans.
  • fed-sim
    PyTorch DP-FedAvg simulator with Dirichlet non-IID client partitions, per-client L2 update clipping, calibrated Laplace/Gaussian DP noise, and drift logging.
Causal & Multimodal Learning
  • uplift-ml
    S-Learner, T-Learner, and 3-stage X-Learner causal CATE estimators benchmarked with Qini coefficient, AUUC, PEHE, and decile lift calibration.
  • fusion-transformer
    PyTorch multimodal classifier fusing FT-Transformer per-column feature tokenizers with transformer text encoders via bidirectional nn.MultiheadAttention.

Core Stack & Tooling

Python PyTorch FastAPI Hugging Face scikit-learn Pandas NumPy SciPy Keras OpenCV pytest SQL Git

Self-hosted SVG telemetry and project showcase cards generated directly from GitHub GraphQL via scripts/generate_profile_cards.py.

Pinned Loading

  1. CM3604_CW CM3604_CW Public

    Automated fact-checking of LLM outputs (FActScore) comparing lexical overlap and DeBERTa textual entailment

    Python 1

  2. chonkie chonkie Public

    Forked from feyninc/chonkie

    🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

    Python

  3. cleanlab cleanlab Public

    Forked from cleanlab/cleanlab

    Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

    Python

  4. DecodeLabs-Internship DecodeLabs-Internship Public

    Applied AI Engineering internship capstones: rule-based guardrails, classification, TF-IDF tech recommender, and OpenCV + Tesseract OCR pipeline

    Python

  5. hiring-agent hiring-agent Public

    Forked from interviewstreet/hiring-agent

    AI agent to evaluate and score resumes.

    Python

  6. seniruvitharanage/domain-ai seniruvitharanage/domain-ai Public

    Jupyter Notebook 1 1