Skip to content
View Jakobish's full-sized avatar

Block or report Jakobish

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.

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
Jakobish/README.md

Hi, I'm Kobi Shahar

Senior engineer building systems that connect human intent to real execution through orchestrated agents, tools, memory, and automation. I focus on agentic workflows built with DAGs, graphs, and dynamic sub-workflows that help AI agents and technology teams work together effectively. My background spans backend engineering, databases, infrastructure, and production operations, helping me build AI systems that are practical, controllable, and maintainable in real environments. ##Core Capabilities

• Agentic workflows, DAGs, graphs, and sub-workflow generation • LLM applications, RAG, GraphRAG, and knowledge systems • Backend, databases, infrastructure, and automation in production environments • Performance, reliability, and maintainability in complex systems • Rapid learning and evaluation of emerging AI tools and workflow architectures

Technical Expertise

AI Systems, Agent Orchestration & Execution Workflows LLMs, RAG, GraphRAG, semantic search, vector retrieval, DAG-based workflows, graph orchestration, and production-oriented agent systems. OpenAI API, Agents SDK, LangChain, LangGraph, CrewAI, Flowise, MCP-related concepts, and AI-assisted development tools. Focused on orchestration, memory, evaluation, human oversight, and real-time visibility. Document Intelligence & Knowledge Systems PDF parsing, document analysis, data extraction, and retrieval-ready knowledge systems. Backend & Full-Stack Engineering TypeScript, Node.js, Next.js, Python, .NET, APIs, backend services, and automation systems. Data & Databases SQL Server, PostgreSQL, query optimization, performance tuning, ETL, and data-intensive application design. Infrastructure, Cloud & Operations Azure, AWS, Docker, PowerShell, Windows Server, IIS, hosting infrastructure, and deployment automation. Professional Experience Senior AI & Software Engineer Independent / Project-Based Work · 2022–Present Focused on AI systems and agent orchestration that connect natural-language requests to coordinated actions across tools, memory, integrations, and real-time visibility. • Built agent-driven workflows connecting human requests to multi-step execution

🛠 What I'm working on

  • Agentic Workflows & MCP: Developing custom servers for the Model Context Protocol to empower LLMs with real-world design and data capabilities.
  • Enterprise RAG Frameworks: Designing high-efficiency AI pipelines that reduce inference costs and improve accuracy.
  • Modern SaaS Architectures: Crafting high-performance, scalable platforms using Next.js, TypeScript, and Supabase.
  • Legacy Modernization: Optimizing complex infrastructure.

Technical Stack

  • AI/Agentic: MCP, LangGraph, RAG, OpenAI SDK, LangChain, Vector Databases (Pinecone/pgvector).
  • Engineering: TypeScript, Next.js, Node.js, Python, .NET.
  • Backend & Systems: PostgreSQL, Supabase, Docker, Hyper-V, PowerShell Automation.
  • Security & Forensics: PDF Internals, OCR Pipelines, QPDF, Malware Detection.

Pinned Loading

  1. PDF-shell PDF-shell Public

    PowerShell

  2. pdforensic_toolkit pdforensic_toolkit Public

    A forensic command-line tool for deep analyzing PDF files

    Python 1

  3. morphic-enhanced morphic-enhanced Public

    TypeScript

  4. ocr-processor ocr-processor Public

    Python

  5. migration_scripts migration_scripts Public

    PowerShell

  6. pdf-renamer-mcp pdf-renamer-mcp Public

    Python