Skip to main content
EKAI Systems

Systems

Engineered systems

Each entry is presented as an architecture: the problem, the shape of the solution, the stack it runs on, and what it did in production.

  • 01Retrieval · Knowledge Graphs · Agentsproduction

    GraphRAG Platform

    Humanloop, 2023 to 2025

    A production retrieval platform whose index is a knowledge graph, so answers can follow relationships between entities across multiple reasoning steps.

    Problem

    Vector similarity alone loses the structure connecting facts. Questions spanning several related entities return fragments that look relevant and reason badly, and no amount of reranking recovers a relationship the index never stored.

    Result

    Supported more than 1,000 active users, with multi-agent orchestration reducing manual analytical workload by roughly half.

    • Python
    • FastAPI
    • Neo4j
    • LangChain
    • Vector databases

    Pipeline

    1. Ingest
    2. Extract
    3. Graph
    4. Retrieve
    5. Synthesise
  • 02NLP · Data Engineeringproduction

    Distributed Semantic Search

    Oxide AI, 2021 to 2023

    Semantic search and retrieval-based question answering across an enterprise document corpus, with the distributed data pipelines needed to keep it current.

    Problem

    Precision degrades as a corpus grows. Retrieval that works over thousands of documents returns plausible noise over millions unless ranking and the ingestion path are engineered together.

    Result

    Processed more than 5 million documents on 100 GB to 500 GB pipelines, improving accuracy and performance by 20 to 35 percent.

    • Python
    • Spark
    • ETL
    • Vector databases
    • AWS

    Pipeline

    1. Ingest
    2. Embed
    3. Index
    4. Rank
    5. Answer
  • 03Computer Vision · Healthcareproduction

    Medical Vision Pipeline

    viso.ai, 2019 to 2021

    Real-time inference over medical imaging, including CT, ECG, and retinal data, built for clinical and industrial deployment.

    Problem

    In diagnostic imaging a false negative and a two-second wait are both failures. Accuracy and latency have to be optimised together, against datasets where edge cases matter more than averages.

    Result

    Reached 92 to 95 percent accuracy while cutting GPU inference latency from roughly two seconds to under 300 milliseconds.

    • Python
    • PyTorch
    • OpenCV
    • GPU inference
    • AWS

    Pipeline

    1. Capture
    2. Preprocess
    3. Infer
    4. Validate

Product Work

Shipped products

Commercial products I have worked on, live and in production.