Skip to content
View shaikn6's full-sized avatar
🎯
Focusing
🎯
Focusing
14 followers · 85 following

Achievements

Achievement: Galaxy BrainAchievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Galaxy BrainAchievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Block or report shaikn6

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. Markdown is supported. 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
shaikn6/README.md

Nagizaaz Shaik

Portfolio LinkedIn Email Hugging Face

I build production GenAI systems for fintech — LLM gateways, RAG pipelines, and multi-agent orchestration — with the backend rigor these workloads demand: idempotency, ACID, audit logging, and CI that gates (-race, govulncheck). 5+ years in data engineering, ML, and cloud; 2+ shipping production LLM systems. Doctoral researcher in Applied AI. AWS ML Specialty certified.

Featured
ledger-service Go Double-entry ledger microservice — idempotent transfers, reversals, deadlock-free row locking, append-only postings. 31 tests, -race, govulncheck clean.
llm-gateway FastAPI One OpenAI-style chat endpoint over Anthropic / OpenAI / Ollama — per-tenant response cache, rate limiting, A/B routing, cost tracking, audit logging. 415 tests, 99% coverage, SDK contract tests.
fintech-devsecops-pipeline Terraform DevSecOps reference platform — hardened Terraform + private EKS, OPA/Rego admission policies with 49 policy tests, Helm chart gated by conftest in CI, multi-scanner CI gate, ArgoCD GitOps.
fin-lora PyTorch · adapters LoRA-tuned Qwen2.5-0.5B for financial sentiment, benchmarked against TF-IDF, FinBERT and zero-shot on tweets, headlines and news. A confidence cascade cuts average latency 63% for 0.4 points of accuracy; a follow-up study measures how easily each model is fooled across five markets.
llm-safety-auditor FastAPI · demo LLM red-teaming — 250+ adversarial payloads, OWASP LLM Top-10 scoring, report generation.
credit-arena scikit-learn Credit-default risk: 6 model families on 30K accounts, compared on AUC, calibration, business cost and fair-lending behaviour with bootstrap significance tests.

Open source

Merged: jackc/pgx #2638 (pool default docs) · mlflow #26613 · langroid #1209 · pyproj #1637 · nibabel #1550 · pystac #1803 · pystac-client #931 · fhir.resources #211
Security: reporter credit on GHSA-m5v3-6ccr-cfgx (sandbox bypass in an AI-agent code executor)
In review: crewAI native Groq / Fireworks / Together providers

Stack

Backend Go · Python · FastAPI · PostgreSQL · Redis  •  LLM / Agents LangGraph · RAG · MCP · OWASP LLM Top 10 · LLMOps
Infra Docker · Kubernetes · Terraform · ArgoCD · GitHub Actions · AWS  •  ML / Data PyTorch · MLflow · Kafka · dbt

Contribution snake

19 public repos · Portfolio · LinkedIn · Hugging Face

Pinned Loading

  1. llm-gateway llm-gateway Public

    LLM gateway: one OpenAI-style chat API over Claude / OpenAI / Ollama with per-tenant response caching, rate limiting, A/B routing, cost tracking and audit logging.

    Python

  2. llm-safety-auditor llm-safety-auditor Public

    LLM red-teaming: 250+ adversarial attacks, OWASP LLM Top 10 scoring, FastAPI audit reports

    Python 1

  3. fintech-devsecops-pipeline fintech-devsecops-pipeline Public

    Production DevSecOps for fintech: Terraform on AWS EKS, Helm + ArgoCD GitOps, Checkov IaC scanning, OPA/Rego admission policies, RBAC, NetworkPolicies.

    HCL

  4. ledger-service ledger-service Public

    Double-entry accounting ledger microservice — idempotent money movement over Postgres, ordered row locking, append-only postings. Go 1.27.

    Go

  5. credit-arena credit-arena Public

    Six credit-default model families on the UCI credit-card data, compared on AUC, calibration, business cost and fair-lending behaviour. Gradient boosting beats logistic regression by +0.0275 AUC (pa…

    Python

  6. fin-lora fin-lora Public

    LoRA-tuned Qwen2.5-0.5B for financial sentiment, benchmarked against TF-IDF, FinBERT and zero-shot on tweets, headlines and news. A confidence cascade cuts average latency 63% for 0.4 points of acc…

    Python