Skip to content
View amwanshul's full-sized avatar

Block or report amwanshul

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 donโ€™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 userโ€™s behavior. Learn more about reporting abuse.

Report abuse
amwanshul/README.md

Hi there, I'm Anshul Wankhede ๐Ÿ‘‹

Typing SVG

B.Tech in Information Technology @ Vishwakarma Institute of Technology (VIT Pune)
Focused on Autonomous Agents, Production RAG Systems, LLMOps, and High-Performance Backends.

LinkedIn GitHub Email


๐Ÿฆ Executive Summary

I build production-grade AI systems, evidence-grounded retrieval pipelines, and backend architectures. Rather than stitching together fragile API wrappers, I engineer from first principles โ€” from mathematical loss functions and numerical optimization to deterministic agent state loops and AST sandboxing.

problem โ†’ mathematical foundations โ†’ system architecture โ†’ prototype โ†’ benchmark โ†’ harden โ†’ ship

๐Ÿง  Latest Engineering Work

Recent work is tracked here to keep the profile tied to concrete engineering output rather than static skill claims.

๐ŸŒ Core Engineering Pillars

๐Ÿง  Agentic Systems

Building autonomous decision systems combining multimodal perception (voice + screen OCR), reasoning graphs, dynamic tool registries, and AST-level safety execution gates.

๐Ÿ”Ž Evidence-First RAG

Engineering enterprise retrieval pipelines with hybrid lexical/dense search (BM25 + Dense), Reciprocal Rank Fusion (RRF), cross-encoder reranking, and empirical evaluation (Recall@K / MRR).

๐ŸŒ Network Security & Systems

Building packet analysis engines, stateful TCP flow trackers, and heuristic intrusion detection systems, alongside low-level C++ algorithmic patterns and mathematical ML optimization from scratch.


๐Ÿ›ฐ๏ธ Spotlight Flagship Projects

Bridging multimodal LLM reasoning directly with real desktop operating system execution.

Platform AI Architecture Security

  • Multimodal Perception: Listens via voice, perceives the active display via screen capture + OCR, and interprets visual context in real time.
  • AST Security Gate: Intercepts generated code using Python's Abstract Syntax Tree (ast) to eliminate arbitrary injection vulnerabilities before system execution.
  • Stateful Execution: Features persistent episodic memory, user approval thresholds for sensitive operations, and dynamic task queuing.
Voice / Screen Perception โ†’ Reasoning Engine โ†’ AST Security Gate โ†’ OS Execution Engine โ†’ Memory Feedback Loop

Evidence-first document intelligence with hybrid retrieval, reranking, citations, abstention, and golden evaluation.

Python FastAPI RAG Eval CI

  • Hybrid Search Engine: Fuses exact lexical matching (BM25 / TF-IDF) with semantic vector search using Reciprocal Rank Fusion (RRF).
  • Cross-Encoder Reranker & Abstention: Re-scores top candidates and enforces a strict confidence threshold โ€” deliberately abstaining when evidence is insufficient to eliminate hallucinations.
  • Deterministic Evaluation: Ships with a golden evaluation harness computing Recall@5 and Mean Reciprocal Rank (MRR), complete with CI automation.
Documents โ†’ Chunker โ†’ [BM25 + Dense Search] โ†’ RRF Fusion โ†’ Cross-Encoder โ†’ Abstention Check โ†’ Grounded Citations

๐Ÿ“Š Complete Engineering Portfolio

Repository Focus Area Key Architectural Signal Stack
๐Ÿง  Sypher Autonomous Agent Multimodal screen perception, Gemini reasoning, and AST-secured OS execution Python โ€ข Gemini โ€ข FastAPI โ€ข WebSockets
๐Ÿง  Agentic Research System Autonomous AI Agents Directed state graph, self-reflection critique loops, AST sandbox & OpenTelemetry tracing Python โ€ข State Graphs โ€ข Tracing โ€ข CI/CD
๐Ÿ”Ž Grounded RAG Lab Enterprise Retrieval Hybrid BM25/Dense search, RRF fusion, cross-encoder reranker & Recall@5 eval Python โ€ข BM25 โ€ข RRF โ€ข FastAPI โ€ข CI/CD
๐ŸŒ Sentinel IDS Network Security & IDS Zero-dependency L2-L7 packet decoder, stateful TCP flow tracking, Port scan, SYN flood, ARP spoofing & DNS entropy heuristics Python โ€ข TCP/IP โ€ข PCAP โ€ข Network Forensics โ€ข CI/CD
๐Ÿ“ ML Foundations ML From Scratch Gradient descent, MSE loss, binary cross-entropy, custom standardizer & metrics Python โ€ข NumPy โ€ข Linear Algebra
๐Ÿ” Semantic Search Lab Information Retrieval Inverted index vocabulary, TF-IDF weighting, L2 normalization & cosine ranking Python โ€ข NumPy โ€ข FastAPI
๐Ÿ‘๏ธ Vision Inspector Computer Vision Classical Canny edge detection, contour geometry, circularity metric & CLI Python โ€ข OpenCV โ€ข Image Processing
๐Ÿง  LeetCode Algorithmic Problem Solving Pattern-oriented problem catalog (Two Pointers, Hashing, DFS, Heaps) in C++ C++17/20 โ€ข Data Structures โ€ข Algorithms

๐Ÿงฐ Technical Arsenal

Tech Skills

  • Core Languages: Python, C++ (17/20), C, Java, SQL, JavaScript/TypeScript
  • AI, ML & Retrieval: RAG Architectures, Hybrid Search (BM25 + Dense), Cross-Encoders, PyTorch, scikit-learn, OpenCV, NumPy, Pandas, Transformers
  • Networks & Security: TCP/IP (L2-L7), Raw Sockets, PCAP Analysis, Network Forensics, Intrusion Detection, ARP/DNS Security
  • Backend & DevOps: FastAPI, RESTful APIs, WebSockets, Docker, Git/GitHub, Linux Environments, GitHub Actions CI/CD

๐Ÿงฎ How I Think & Build

  • Systems over Wrappers: An LLM without a deterministic state graph, security boundaries, and evaluation is just a toy. True AI engineering lives in the architecture around the model.
  • Empirical Evaluation: If you can't quantitatively measure your retrieval quality (Recall, MRR), latency, and failure cases, you cannot improve them.
  • Mastery from First Principles: Understand the math, the loss surface, and the gradient equations before importing high-level library abstractions.

๐Ÿ“ˆ GitHub Analytics & Live Activity




Always Learning. Always Building. Engineering from First Principles.

Interested in collaborating or discussing AI systems? Let's connect!

LinkedIn Email

Popular repositories Loading

  1. Sypher Sypher Public

    AI-powered desktop automation system combining natural-language commands, tool execution, multimodal input, and local system control.

    Python 3

  2. amwanshul amwanshul Public

    Personal engineering profile & portfolio hub โ€” AI Systems, RAG pipelines, and Agentic workflows.

  3. Leetcode Leetcode Public

    Curated C++ implementations of Data Structures and Algorithms organized by core problem-solving patterns.

    C++

  4. ml-foundations ml-foundations Public

    Transparent implementations of machine-learning algorithms from mathematical scratch (gradient descent, regressions, custom standardizer, metrics).

    Python

  5. semantic-search-lab semantic-search-lab Public

    Transparent document-search API exploring TF-IDF retrieval, cosine similarity, top-k ranking, and FastAPI serving.

    Python

  6. vision-inspector vision-inspector Public

    Computer vision inspection pipeline using OpenCV for Canny edge detection, contour geometry, and measurement analysis.

    Python