Ram Pakanayev

    Ram Pakanayev

    AI E

    Specialization in production-grade Generative AI platforms, GraphRAG, RAG, and other RAG-based architectures. Expertise in autonomous agentic workflows with advanced context handling and memory management. Implementation of secure, self-hosted enterprise solutions utilizing AWS cloud-native services. Integration and creation of Model Context Protocol (MCP) for real-time data capabilities.

    AI Engineering Experience

    Senior AI Engineer with hands-on experience building GraphRAG platforms, Multi-Agent systems, and enterprise GenAI solutions at leading Israeli tech companies.

    2025 – Present
    Elad Software Systems logo

    AI Engineer

    Elad Software Systems• Tel Aviv
    • Architected CodeAI, a secure B2B GenAI platform with dual-backend architecture (GraphRAG + Vector), ensuring proprietary code sovereignty.
    • Engineered a hybrid retrieval system combining Neo4j knowledge graphs with PostgreSQL/pgvector, modeling AST nodes, inheritance, and function calls for superior context.
    • Designed autonomous LangGraph agents for legacy SQL modernization with 95% intent accuracy using Claude 3.5 Sonnet.
    • Built on-demand database provisioning service using Docker SDK for isolated environments per project.
    • Integrated multi-provider Git ecosystem (GitHub, GitLab, Bitbucket, Azure DevOps) with OAuth and HMAC-SHA256 verification.
    • Developed a serverless audio processing platform handling concurrent workloads for enterprise clients with near-zero latency.
    LangGraphAWS BedrockNeo4jPostgreSQLpgvectorDocker SDKFastAPISystem ArchitectureOAuth 2.0
    2023 – 2025
    MeComics logo

    Full Stack AI Engineer

    MeComics• Tel Aviv
    • Led the launch of an AI-driven B2C SaaS platform, delivering a functional MVP in under 3 months.
    • Architected a multimodal Text2ComicPage pipeline combining GPT-4 (text) and Stable Diffusion (image).
    • Implemented advanced features like character persistence, regeneration, and reference-image conditioning using ControlNet.
    • Served as technical lead for 13 major system components and 50+ features, aligning technical decisions with business goals.
    • Reduced comic creation time by 83% and boosted user retention by 42% through UX optimization.
    GPT-4Stable DiffusionControlNetReactNode.jsAWSSaaSTechnical LeadershipProduct Development

    Education

    Bachelor of Science in Computer Science

    2020 – 2023
    Holon Institute of Technology

    Comprehensive education in computer science fundamentals, algorithms, data structures, software engineering principles, and emerging technologies. Focus on practical application and real-world problem-solving.

    Key Areas of Study

    Data Structures & Algorithms
    Software Engineering
    Database Systems
    Computer Networks
    Machine Learning
    Artificial Intelligence
    System Design
    Mathematics for CS

    Notable Achievement

    Graduated with strong focus on emerging AI technologies and practical software development, providing the foundation for advanced work in machine learning and artificial intelligence.

    Production AI Projects

    Real-world AI systems built with GraphRAG, Multi-Agent orchestration, and SageMaker BYOC— not proof-of-concepts, but production-grade platforms serving enterprise clients.

    Enterprise Code Intelligence Platform

    Secure, self-hosted GenAI platform designed for strict data sovereignty. Implemented a dual-backend architecture (GraphRAG + Vector) to power autonomous agentic workflows for legacy code modernization.

    Enterprise Code Intelligence Platform
    • Dual-backend GraphRAG + Vector architecture
    • Autonomous agentic workflows
    • Secure self-hosted enterprise solution
    LangGraphNeo4jGraphRAGAWS BedrockClaude 4.5 SonnetPostgreSQLpgvectorDocker SDKFastAPIAWS CognitoReactTypeScriptMicroservices

    Hebrew Voice Agent

    Advanced voice-to-voice agentic system powered by Strands. Features real-time orchestration of STT, LLM, and TTS. Deployed multiple fine-tuned Hebrew TTS models from Hugging Face to SageMaker (BYOC) to evaluate which performed best for production use.

    Hebrew Voice Agent
    • Powered by Strands Agent Framework
    • SageMaker BYOC deployment for Hebrew TTS models
    • Real-time voice-to-voice orchestration
    Strands Agent SDKAWS BedrockClaude 3.5 HaikuAmazon TranscribeSageMaker BYOCAWS ECRAmazon PollyWebSocketsRAG-liteNext.jsTailwind CSSPythonDocker

    Cloud-Native Audio Transcription & Analysis

    Serverless audio processing platform handling concurrent workloads with near-zero latency and multilingual AI summarization. Built with AWS Transcribe, Bedrock, and FastAPI.

    Cloud-Native Audio Transcription & Analysis
    • Near-zero latency transcription
    • Multilingual AI summarization
    • Serverless concurrent processing
    AWS TranscribeAWS BedrockFastAPIWebSocketsClaude 4.5 OpusAsyncIOServerlessAWS LambdaAPI GatewayPCM Audio ProcessingMedical AI

    Consensus Chat - Multi-Agent AI Debate Platform

    Real-time multi-agent AI debate orchestrator featuring sequential agent processing, live influence tracking via meta-LLM analysis, and force-directed graph visualization of idea propagation across Claude, GPT-4, Gemini, Grok, and LLaMA.

    Consensus Chat - Multi-Agent AI Debate Platform
    • Sequential multi-agent debate orchestration
    • Real-time influence analysis with meta-LLM
    • Live D3 force-directed network visualization
    LangGraphFastAPIReactTypeScriptD3.jsRechartsAnthropic SDKOpenAI SDKGoogle GenAIxAI SDKOllamaWebSocketsTailwindCSSViteUvicorn

    MeComics AI Platform

    AI-driven B2C SaaS platform for personalized comics, featuring a multimodal Text2ComicPage pipeline combining GPT-4 and Stable Diffusion. Delivered MVP in under 3 months.

    MeComics AI Platform
    • Multimodal Text2ComicPage pipeline
    • MVP delivered in <3 months
    • Personalized comic generation
    GPT-4Stable DiffusionControlNetReactNode.jsPrompt EngineeringMultimodal AISaaSFramer MotionStripeMongoDB

    AI Engineering Skills

    Full-stack AI capabilities from LLM orchestration to cloud deployment— Python, TypeScript, LangChain, AWS, and modern ML infrastructure.

    AI/ML & Generative AI

    LangGraphLangChainHybrid GraphRAGMulti-Agent SystemsMCPLLM EvalsPrompt EngineeringStable DiffusionControlNet

    Cloud & MLOps

    AWS BedrockSageMakerAWS LambdaDockerKubernetesLLMOpsCloudFormationCloudWatch

    Languages

    PythonTypeScriptJavaScriptSQLC#

    Backend & Protocols

    FastAPIWebSocketsSSE StreamingAsync MicroservicesREST APIs

    Databases

    Neo4jAWS NeptunePostgreSQL (pgvector)MongoDBOpenSearchDynamoDB

    Frontend & Tools

    React.jsNext.jsTailwind CSSGitAzure DevOpsFigma