← Back to Students
Rivka S.
Bio
Software developer with strong logical reasoning, excellent interpersonal communication, and proven teamwork skills. Experienced in backend development, AI-driven orchestration using LangChain and LLM tools, and building scalable microservice-based systems. Academic background includes machine learning and deep learning. Python · C# · ASP.NET Core · React · RabbitMQ · Redis · LangChain · Docker
Skills
Python
C++
Node.js
.NET
React
TypeScript
Docker
Redis
RabbitMQ
FastAPI
WebSockets
fastmcp
LangChain Agents
Prompt Engineering
Pydantic
Embedding Models
AsyncIO
System Design
github
Bootcamp Project
Comprehensive testing framework for software quality assurance
Mentored by: Quinn
Data Science Bootcamp 2025 (Data)
Responsibilities:
Built the initial MCP-based orchestrator using Python, FastMCP, asyncio, establishing the system’s multi-service execution architecture.
Developed a fully generic Plan Generator using Pydantic, JSON Schemas, async Python, and structured validation logic.
Built the schema-driven Plan Reviewer using Pydantic models, structured evaluators, JSON-based rule definitions, and clean async flows.
Implemented the LLM Factory using factory patterns, environment-driven config, Gemini API, OpenAI API, enabling effortless model switching.
Upgraded the orchestrator into a LangChain Agent using StructuredTools, reasoning loops, LangChain callbacks, and efficient memory handling.
Created the MCP Tools Registry with dynamic Pydantic model generation, JSON schema parsing, runtime tool injection, and LangChain integration.
Implemented the Ask-User mechanism using WebSocket, asyncio, bidirectional messaging, enabling real-time clarification mid-execution.
Integrated RabbitMQ RPC using pika, message queues, correlation IDs, distributed workers, ensuring scalable and fault-tolerant execution.
Built the Orchestrator–Workers Bridge using RabbitMQ envelopes, JSON-RPC patterns, MCP-style schemas, and unified messaging logic.
Added Redis caching + semantic caching using Redis-py, embeddings, hashed contexts, reducing LLM calls and improving runtime performance.
Click to enlarge
Additional Projects
Appointment Management System (React, ASP.NET Core, SQL Server)
A full-stack medical scheduling and patient-management system.
• Built a scalable multi-layer backend with availability rules, automated scheduling logic, and secured REST APIs (ASP.NET Core + SQL Server).
• Developed a modular React interface with multi-field search, role-based dashboards, reusable components, Redux Toolkit state management, and react-hook-form validation.
English Level
Working Proficiency