Victor Cuellar
ENES

Victor Cuellar

Machine Learning Engineer

Santa Cruz de la Sierra, Bolivia

I’m a Machine Learning Engineer with a background in backend development. I work mainly with Python and Go on document processing, semantic search, and applications built around large language models. My work includes retrieval-augmented generation, knowledge graphs, and data privacy, with attention to evaluation, testing, and reliability.

Pages become passages. Passages become connections.

Selected work

Document processing, retrieval and graph-guided planning, shown through illustrative interfaces.

go-ms-rag

A Go service that finds relevant document passages before generating an answer.

  • Text and file ingestion
  • Document filtering before generation
  • Fixed response when evidence is absent
Query console
Keep scores ≥ 0.55 × the top score, up to the context budget.Context budget: 5 · Retained: 3

Showing 1 of 5 retrieved passages.

Tool loansPassage 1

Members may borrow one repair stand for two days. Return the stand clean before the workshop closes.

Illustrative similarity0.92
Answer from the excerpts

Members may borrow one repair stand for two days. It must be returned clean before the workshop closes.

Fixed illustrative scores, not measured retrieval quality.

Illustrative simulation with fixed example data. No live model or service is called.

Figure 1. An illustrative interface for finding passages and answering from a document collection.

AxiomEngine

A Go service that builds prerequisite-ordered study plans from declared assessment deficits.

  • Curriculum knowledge graph
  • Parallel planning by topic
  • Graph-derived prerequisites and priorities

Study plan builder

Prerequisite map

Full prerequisite chains, in study order.

Variables
Objects
Classes
Inheritance
Polymorphism
Study plan
  1. 1
    VariablesIllustrative resources: diagramIllustrative resources: video
  2. 2
    ObjectsIllustrative resources: diagramIllustrative resources: video
  3. 3
    ClassesIllustrative resources: diagramIllustrative resources: video

+2 additional topics

subgraph_tuples
5
topics_processed
1
items_generated
5
items_after_validation
5

Illustrative simulation with fixed example data. No live model or service is called.

Figure 2. An illustrative interface for turning declared assessment deficits into a prerequisite-ordered plan.

Student resource platform

  • Resources
  • Support
  • Résumé

A self-initiated project for students of FICCT at UAGRM: a resource portal, support platform, and browser-based résumé generator.

An independent project, not affiliated with or endorsed by the university.

Experience

  1. May 2025 – Present

    NVISIONx

    Machine Learning Engineer

    Develop machine learning and backend services for document classification, sensitive-data detection, and knowledge retrieval. Build and evaluate LLM-based workflows, improve information extraction, and address reliability in document processing.

  2. Oct 2024 – Apr 2025

    SS Ventures

    Machine Learning Engineer; Back End Developer

    Concurrent roles

    Built LLM-based features for document search, automated tagging, and recommendations. Developed real-time Python services and asynchronous processing for conversational applications and document retrieval.

  3. Aug 2022 – Sep 2024

    Jungle

    Machine Learning Engineer; Back End Developer

    Concurrent roles

    Developed conversational AI and semantic search for internal knowledge access. Integrated applications with workplace tools and managed cloud deployment infrastructure.

  4. 2018 – 2022

    Fiverr

    Freelance Software Developer

    Developed custom software for clients, translating requirements into application features and adapting implementations to each project’s scope.

About

I have developed software since 2018. My background is in backend engineering, and my current focus is machine learning: document processing, search, and applications built around language models.

Languages
Python, Go, TypeScript, SQL
Backend & data
Django, FastAPI, Celery, PostgreSQL, Redis
Retrieval & LLM applications
LLMs, LangChain, LangSmith, RAG, GraphRAG, information extraction, semantic search, clustering, Pinecone, model evaluation
Infrastructure & testing
AWS, Docker, Nginx, GitHub Actions, pytest, Playwright

Education

Universidad Autónoma Gabriel René Moreno (UAGRM)

Spoken languages

  • SpanishNative
  • EnglishFull professional proficiency
  • PortugueseLimited working proficiency

Contact

Let’s talk about document processing, search, and dependable machine learning systems.