EVIDENCE DOSSIER
Request Intro
// PRODUCTION DEPLOYMENTS & ARCHITECTURAL CASE STUDIES · SECTION 04

Flagship Systems & Production Impact

Technical architecture breakdowns of production systems, projects, and repositories this candidate has attached to their dossier.

// INTERVIEW ENGINE

Interview Engine is arriving soon....

SYSTEM 01 // PROJECTROLE: FEATURED PROJECT

Agentic Code Editor

Built an interactive CLI code-editing agent using a LangGraph pipeline (clarifier, analyzer, planner, editor, validator) that turns a natural-language requirement into reviewable code changes on a target project. Implemented Python AST indexing to select relevant files/snippets, and an LLM-backed planner emitting structured JSON edit operations applied with file backups, rollback, and compile-based validation with auto re-planning on failure.

TechnologyLangGraph
StackPython
PlatformAST
Metric 01—Pending
Metric 02—Pending
Metric 03—Pending
View Project

// INTERVIEW ENGINE

Interview Engine is arriving soon....

SYSTEM 02 // PROJECTROLE: FEATURED PROJECT

RAG Documentation Assistant

Built a FastAPI RAG service (ask endpoint) that ingests local documents, chunks them, and embeds the chunks with Sentence-Transformers into a Qdrant vector store run via Docker Compose. Implemented hybrid retrieval combining BM25 keyword search with vector search to maximize candidate recall, then reranked candidates with a cross-encoder to boost precision before passing the top chunks to the LLM. Implemented retrieval-grounded answer generation via the Groq API.

TechnologyFastAPI
StackQdrant
PlatformGroq
Metric 01—Pending
Metric 02—Pending
Metric 03—Pending
View Project

// INTERVIEW ENGINE

Interview Engine is arriving soon....

SYSTEM 03 // PROJECTROLE: FEATURED PROJECT

CreditWise – Loan Approval Prediction

Built an end-to-end supervised ML pipeline to predict loan approval as a binary classification problem, benchmarking KNN, Logistic Regression, and Naive Bayes on applicant financial and credit data. Performed EDA and feature engineering on applicant demographic and financial attributes, then evaluated models using Precision, Recall, and F1-score to select the best-performing classifier.

TechnologyPython
Stackscikit-learn
PlatformKNN
Metric 01—Pending
Metric 02—Pending
Metric 03—Pending
View Project

// INTERVIEW ENGINE

Interview Engine is arriving soon....

SYSTEM 04 // PROJECTROLE: FEATURED PROJECT

T5 Text Summarizer

Fine-tuned a T5 transformer for abstractive dialogue/text summarization and deployed it as a FastAPI microservice with a React (Vite) frontend, orchestrating both services alongside Redis via Docker Compose. Engineered a Redis caching layer keyed on SHA-256 hashes of input text (1-hour TTL) to skip redundant model inference on repeated requests, with automatic fallback to direct inference if Redis is unavailable. Tuned beam-search decoding for coherent summary generation.

TechnologyFastAPI
StackPyTorch
PlatformTransformers
Metric 01—Pending
Metric 02—Pending
Metric 03—Pending
View Project

// INTERVIEW ENGINE

Interview Engine is arriving soon....

SYSTEM 05 // PROJECTROLE: FEATURED PROJECT

EfficientNet-based Binary Classification Model for Melanoma Lesions

Built an EfficientNet-based binary classification model to distinguish benign vs. malignant melanoma lesions on a 10K+ image dataset. Evaluated model robustness against adversarial attacks (BIM, PGD via Torchattacks) and implemented an SVD-based defense mechanism.

TechnologyEfficientNet
StackTorchattacks
PlatformSVD
Outcome91.45% validation accuracy on a 10K+ image dataset; accuracy dropped to 73.79% under BIM attackSelf-reported
Metric 02—Pending
Metric 03—Pending
View Project

// INTERVIEW ENGINE

Interview Engine is arriving soon....

SYSTEM 06 // REPOSITORYROLE: OPEN SOURCE

nidhitk

nidhitk

Language—
Topic—
Topic—
Stars1GitHub indexed
Metric 02—Pending
Metric 03—Pending
View Repository

// INTERVIEW ENGINE

Interview Engine is arriving soon....

// INTERVIEW ENGINE

Interview Engine is arriving soon....

// RECRUITMENT & ADVISORY ENGAGEMENTS

Request Technical Architecture Dossier

Full verification packet containing source artifacts, production traces, and formal proofs available for prospective leadership roles once attested.

Download PDF (Signed)Request Intro
EXECUTIVE CANDIDATE INTAKE

Hiring for Software Engineer?

Request the full evidence dossier — verified interview sessions, cryptographically attested artifacts, and reference outcomes.

Request IntroDownload PDF (Attested)
BUILT ON INTERVUES VERIFICATION PROTOCOL // EVERY CLAIM TRACED TO CRYPTOGRAPHIC SOURCE
KEY: —