Skip to content
Leon Achata
Portrait of Leon Achata

Available for freelance projects

Leon Achata

Software Engineer · Generative AI

I'm a software engineer specializing in generative AI, with six years in data and AI, from medical NLP in healthcare to multi-agent platforms on AWS. I trained as a biomedical engineer at PUCP.

Today I build enterprise GenAI for Apple through TCS: LLM pipelines, RAG and agent orchestration that connect internal tools into end-to-end workflows, taken from proof of concept to production with teams across the Americas and APAC, entirely in English.

With clients I work end to end (architecture, backend, the interface people actually use, and deployment), whether that's an AI system or a full website. One engineer accountable for the whole thing, with clear scope and a clean handover.

Based in Montevideo (UTC−3). My day overlaps the full US workday.

Now
GenAI Engineer · Apple (via TCS)
Experience
6+ years in data & AI engineering
Languages
English (C2, EF SET 82/100) · Spanish (native) · Portuguese
Download CV (PDF)

Certified

Claude Certified×4

  • Associate
  • Developer
  • Architect Foundations
  • Architect Professional
  • AWS Certified AI Practitioner
  • AWS Certified Cloud Practitioner
  • IBM Machine Learning Professional
  • EF SET English Certificate82/100 · C2 Proficient

Services

What I can build for you

AI systems where language models pay for themselves quickly, and the websites around them. Each one starts with a free discovery call and a fixed-scope proof of concept.

Document processing

Invoices, IDs, contracts and forms turned into validated, structured data, straight into Excel, your database or your ERP.

What you get

  • Extraction pipeline with validation steps
  • Review screen for the edge cases
  • API and export to the tools you already use

Knowledge assistants

A chat assistant that answers from your own documents and shows where each answer came from. Private, searchable and measurable.

What you get

  • Ingestion and hybrid search (semantic + keyword)
  • Answer-quality evaluation on your questions
  • Deployment on AWS or your current stack

Agents & workflow automation

Multi-step agents that connect your tools (email, Slack, ticketing, internal APIs) and take repetitive work off your team's plate.

What you get

  • LangGraph orchestration with human checkpoints
  • Tool integrations through MCP
  • Logging plus cost and latency tracking

Talk to your data

Let non-technical people query your databases in plain English, with guardrails so the model can never run unsafe SQL.

What you get

  • Plain English to validated, read-only SQL
  • Follow-up questions and conversational filters
  • Access rules on what each user can see
Built before inSQL Agent

Websites & web apps

Fast, accessible websites for organizations that need more than a template, with their own back end, forms, integrations and the hosting to run them.

What you get

  • Design and build in React / Next.js
  • Back end for forms, records and e-mail
  • Deployment, HTTPS, backups and maintenance

Selected work

Selected work

Open-source AI systems with their code, and websites running in production for real organizations.

Everything on GitHub
  • Web

    Enaki

    enaki.edu.pe

    The full web ecosystem of a teacher-training institution: a public site for programs, courses and news, an API for contact and complaints, and a Moodle virtual campus, all on infrastructure I set up and maintain.

    React 19ViteTailwind
  • Web

    Waymaku

    waymaku.edu.pe

    The institutional site of the education association behind Enaki: open research, free resources on intercultural education, an opinion blog and a souvenir shop, backed by its own API on the same kind of hardened infrastructure.

    React 19ViteTailwind
  • Web

    República de Chile

    rch.edu.pe

    A new website for a public secondary school with more than 90 years of history, replacing its old WordPress site: admissions, school life, an online document desk and contact, published automatically to the school's own hosting.

    React 19ViteTailwind
  • Data

    SQL Agent

    Ask any SQL database questions in plain language. Every query is checked by a parser before it runs, read-only.

    LangGraphClaudesqlglot
  • RAG

    DocuChat

    Grounded answers from your documents, with citations down to the exact sentence, and an honest “not in the documents” when that is the truth.

    LangGraphClaudepgvector
  • Agents

    Toolbox Gateway

    A self-hosted platform for tool-using agents: one gateway to OpenAI, Gemini and Bedrock, tools served over MCP, and every step traced with cost.

    LangGraphMCPFastAPI

Stack

Tools I use in production

GenAI & agents

LangChainLangGraphLangSmithMCPA2AGoogle ADKAWS BedrockOpenAIOllamapgvectorFAISSChromaDB

Backend & data

PythonFastAPIPydanticPostgreSQLMySQLMongoDBRedisPySpark

Cloud & ops

AWS LambdaEKS / ECRS3RDSDynamoDBCloudWatchAWS CDKDockerKubernetes

Frontend & product

TypeScriptReactNext.jsNode.jsTailwind CSS

Engineering practice

System designAPI designLLM evaluationObservabilityAutomated testingCI/CDInfrastructure as code

Process

How a project runs

  1. 01

    Discovery call

    30 minutes. You walk me through the problem; I ask about volume, systems and constraints. You leave with an honest answer on whether AI is the right tool.

  2. 02

    Proof of concept

    One to two weeks on your real data. A working version you can click, plus the numbers that matter: accuracy, cost per run, latency.

  3. 03

    Production build

    Hardening, integrations, evaluation and deployment on your cloud. Weekly demos, no black boxes.

  4. 04

    Handover & support

    Documentation, code in your repository and a support window after launch. You own everything.

Experience

Where I've worked

  1. Mar 2026 - Present

    Apple · via TCS

    GenAI Engineer · Montevideo, UY

    Design and build enterprise GenAI automation for internal workflows: LLM pipelines, RAG and agent orchestration integrated with collaboration tools, taken from proof of concept to production. Daily work with engineering teams across the US and APAC.

  2. Sep 2025 - Feb 2026

    JLR Analytics

    AI Engineer · Lima, PE

    Built multi-agent systems with LangChain, LangGraph and MCP, deployed on AWS (EKS, ECR, Bedrock, S3, DynamoDB, CloudWatch). RAG with pgvector and local models, document chatbots with OCR and speech-to-text, and agent orchestration for an AI-driven robotic arm for POS systems.

  3. Apr 2025 - Sep 2025

    Universidad Peruana Cayetano Heredia

    AI/ML Developer · Lima, PE

    Agents and conversational workflows for research teams; RAG systems with FAISS and ChromaDB; reproducible pipelines for text, image and structured data.

  4. Oct 2023 - Mar 2025

    Cardiomed SAC

    AI/ML Developer · Data Scientist · Lima, PE

    Transformer models for medical text classification and information extraction, LangChain assistants for internal medical queries and automated technical reports, and Python workflows for data analysis.

  5. Jan 2020 - Oct 2023

    Asociación Educativa Waymaku

    Data Scientist · Data Analyst · Lima, PE

    Where it started: data analysis, reporting and the first machine learning models.

Contact

Have a process that eats hours every week?

Tell me about it. The first call is free, and you'll come away with a clear idea of what's possible and what it would take.

Write to me at

leonyemin@gmail.com

Send a message

FAQ

Before we talk

How do you price projects?

After the discovery call I send a fixed-scope proposal for the proof of concept, so you know the cost before any work starts. Production work can be fixed-scope or a monthly retainer, whatever fits the project.

Is my data safe with you?

I'm used to enterprise security requirements. I can sign an NDA, work inside your own cloud account, and use models that don't train on your data (AWS Bedrock, Azure OpenAI or self-hosted open-source models).

Which language model will you use?

Whichever fits your cost, privacy and quality needs: OpenAI, Anthropic Claude, models on AWS Bedrock, or open-source models. During the proof of concept I show you the trade-offs measured on your own data.

Who owns the code?

You do. The code lives in your repository, with documentation and a handover session so your team can run and extend it.

How much availability do you have?

I take on a small number of freelance projects at a time so each one gets focused attention. Tell me your timeline on the call and I'll be straightforward about whether I can meet it.