Bruno Leite's CV

• Email: contact@brunoleite.co
• Location: Garopaba, SC, Brazil
• Website: brunoleite.co
• LinkedIn: brunoconterleite
• GitHub: brunocleite

Summary

AI engineer who writes the code. Currently co-founder and CTO of octoATHLETE, where I am also the principal engineer on the platform — personally authoring roughly 55% of all commits — building a production multi‑agent LLM system that turns clinicians' voice notes and multi-source sports telemetry into decision support for professional sports teams.

Day-to-day I design and implement agent architectures, prompts and tool schemas, evaluation harnesses, and the data and inference pipelines underneath them — nine production agents on Mastra, schema‑constrained generation validated with Zod, LLM‑as‑judge and golden‑set evals, and quota‑aware batch inference across Amazon Bedrock and OpenRouter. Twenty years of backend and cloud architecture (Java, TypeScript, Python, AWS) behind it, so the AI ships as a reliable system — versioned, observable, tenant‑isolated and cost‑controlled — rather than a demo.

Experience

Co-founder & CTO / Principal AI Engineer, octoATHLETE -- Bollington, UK (Hybrid)

July 2024 – present

• Principal engineer as well as CTO — personally authored ~1,550 of the platform's 2,800 commits (≈55%), spanning the agent layer, data lakehouse, API contracts and AWS infrastructure of an AI athlete health-monitoring SaaS for professional sports teams.

• Built and shipped nine production LLM agents and four orchestrated workflows on Mastra — clinical voice-note extraction, longitudinal wellness synthesis, training-load analysis, post-match assessment, a tool-calling readiness assistant and a safety guardrail agent.

• Designed a capability-based model router across Amazon Bedrock and OpenRouter (Claude Sonnet, GPT‑5 class, gpt‑oss‑safeguard) so agents request a capability rather than a model, pinning all health-data inference to in-region Bedrock for UK data residency.

• Kept authoritative scoring deterministic in code and used LLMs only for grounded narrative — schema-constrained generation via Bedrock Converse tool calling, validated with Zod, malformed output rejected and retried against the failed contract.

• Authored the clinical extraction prompts enforcing verbatim evidence spans, recency and staleness gates and explicit no-diagnosis rules, making every model assertion traceable back to the source dictation.

• Built the evaluation stack — a golden-set harness over real clinical dictation scoring capture, accuracy and false-positive rates independently, plus deterministically sampled LLM-as-judge scoring on 15% of live production traces.

• Ran quota-aware batch inference through a Dagster and Apache Iceberg lakehouse, fingerprinting prompt, model and content hashes to cache extractions and invalidate them on semantic change; tuned concurrency against Bedrock token admission limits.

• Implemented the streaming chat layer (SSE over the AI SDK protocol) with prompt caching and per-step token accounting, cutting stream payload ~99% and hardening it against client-forged tenant context.

• Deployed and operate the stack on AWS with SST and Pulumi — Mastra on ECS Fargate, Lambda, Aurora, DynamoDB, Trino — filtering sensitive data in the AI trace exporter, and led three engineers to a near-zero defect rate as architect and reviewer.

Lead Software Engineer & Technical Architect, Gendo -- Remote

June 2024 – July 2025

• Established an AI‑assisted development methodology that enabled a 300%+ increase in developer productivity.

• Led a cross‑functional team of five developers as project leader, owning architectural design and implementation standards end to end.

• Drove strategic technical decision-making to keep solutions scalable and maintainable across all development initiatives.

• Set organisational standards for development practice, code quality and release process, reinforced through hands-on reference implementations and mentorship.

Development Lead, FalconHR -- Remote

Aug 2023 – Mar 2024

• Architected and built a multitenant next‑generation HR SaaS platform, classified as "very sophisticated" by AWS architects.

• Created a CI/CD pipeline able to deploy serverless applications together with their infrastructure in under ten minutes.

• Defined DynamoDB working guidelines following current single‑table design standards and designed a data ingestion pipeline built on DynamoDB streams.

• Delivered the entire project's infrastructure as code with AWS CDK and SST, and guided service selection across Lambda, Step Functions, Cognito, SQS and SNS.

• Established foundational code standards, testing methods and repository organisation, and hosted 50+ pair‑programming sessions to spread them across the team.

Full-stack Engineer, PLS Logistics Services -- Remote

Jan 2023 – Aug 2023

• Maintained and developed AI/ML components that automated document revision and invoice release, materially improving operational efficiency.

• Introduced new testing standards using Java, Spring and PostgreSQL, raising overall software quality and reliability.

• Refactored and modernised legacy components in a time‑sensitive environment, improving performance and reducing technical debt.

Cloud Architecture Consultant, Catalyst UX (An Unosquare Company) -- Remote

Aug 2022 – Jan 2023

• Defined and enforced project architecture, build, code and test standards for a Node.js, TypeScript and AWS CDK application.

• Built a shared library enabling other developers to create on-the-fly deployment pipelines with AWS CodePipeline, AWS CDK and TypeScript.

• Created unit-test standards for AWS CDK and AWS Lambda TypeScript components, plus build scripts and automated library releases via semantic‑release.

• Led a significant refactoring that improved adherence to AWS CDK standards and overall code organisation.

Senior Java Development Consultant, STEP -- Jersey (Remote)

Mar 2021 – Oct 2022

• Maintained and improved an application aggregating data from multiple banks to analyse investment strategies.

• Cut call times across the codebase by optimising SQL queries and JPA implementations.

• Split the project into microservices and created the GitHub Actions deployment jobs, Dockerfiles and server setup scripts behind it.

• Built an asynchronous background file processor using Amazon SQS and S3 to accelerate XLS uploads.

Senior Java Engineer, SWYP -- Remote

Sept 2021 – Mar 2022

• Maintained and improved a microservices deployment pipeline to Amazon ECS using Docker and CircleCI.

• Delivered fixes and improvements across Spring Boot microservices integrating Firebase, MySQL, AWS SQS and AWS S3.

Back-end Engineer, Shoshin Works -- Remote

Mar 2021 – Sept 2021

• Built an application for NASA to predict the future of aviation, feeding multi-source data through an NLP processor into predictive visualisations.

• Integrated SerpApi and the Zyte API to streamline data acquisition from Google services and raw HTML sources.

• Designed abstract Java components that made adding new external services straightforward, backed by Spring Data and MongoDB Atlas.

Java Software Engineer, Wearsafe Labs -- Remote

Jan 2019 – May 2021

• Developed Java AWS Lambda functions processing IoT messages from personal safety devices, with AWS IoT rules and Kinesis streams feeding them.

• Created a critical‑section locking mechanism to handle parallel device messages and prevent concurrent state corruption.

• Built a continuous-delivery strategy achieving zero‑downtime production deployments with rollback, plus an end‑to‑end test platform covering AWS IoT → Kinesis → Lambda → DB.

• Redesigned the database integration-test architecture, making tests up to five times faster with one third of the code.

• Eliminated duplicate message processing with Memcached on AWS ElastiCache and instrumented the API with AWS X‑Ray tracing.

Lead Software Architect, Dandelion Development -- Remote

July 2019 – Nov 2019

• Lead architect for an ERP-to-CRM integration with a data warehouse, defining the Spring Boot 2 project structure and building most of the application.

• Created the integration layer interacting with the ERP and CRM sides using the Spring 5 WebClient, and led two other developers.

• Established a test-case structure per code sector — controllers, database, entities — achieving 75%+ overall coverage.

Java Engineer, Project44 -- Remote

Jan 2018

Built carrier integrations on the P44 API, mapping external provider models onto internal modelling with full unit and integration test coverage.

Java Lead Engineer, Aon Inpoint -- Remote

2017 – 2018

Architected a Java 8 / Spring Boot survey and benchmarking platform — REST services, multi-language surveys, an email queue, JWT security and a Docker/CircleCI pipeline.

Senior Java Software Engineer, IBM -- Porto Alegre, Brazil

2013 – 2015

Built Jakarta EE components (SOAP/REST, JPA, TDD) and cloud environments for the IBM Liquid crowdsourcing platform; automated deployments and WebSphere management in Python.

Senior Java Software Engineer, ADP -- Porto Alegre, Brazil

2011 – 2012

Developed security-focused Java components for ADP's portal application and contributed to its migration to a PaaS model.

Education

Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS), BS in Computer Engineering -- Porto Alegre, Brazil

2005 – 2013

Open Source and Writing

• spring-boot-exception-handling — reference implementation for REST API error handling. 491 stars, 275 forks. The companion article is published on the Toptal Engineering Blog.

• Guide to Spring Boot REST API Error Handling — long-form technical article, Toptal Engineering Blog.

• setup-sst — GitHub Action that provisions SST v3 (ION) with dependency caching.

Certifications

Oracle Certified Professional, Java SE Programmer

May 2011

Oracle

Skills

AI Engineering: Agentic LLM systems, Mastra, Vercel AI SDK, Amazon Bedrock, OpenRouter, Anthropic Claude, tool/function calling, schema‑constrained generation (Zod/JSON Schema), prompt engineering, LLM evals (golden sets, LLM‑as‑judge), guardrails, streaming (SSE), prompt caching and token cost control, batch inference, MCP, AI‑assisted development

Languages: Python, TypeScript, JavaScript, Java, SQL, HTML, CSS

Cloud & Serverless: AWS (Bedrock, Lambda, ECS/Fargate, DynamoDB, S3, Cognito, Step Functions, SQS/SNS, API Gateway, IoT, X‑Ray), Serverless, AWS CDK, SST, Pulumi, Terraform, Docker

Data & Pipelines: PostgreSQL, Apache Iceberg, Dagster, Trino, SQLMesh, Prisma, Amazon DynamoDB, MySQL, MongoDB, Amazon S3

Frameworks: Node.js, Hono, React, Svelte/SvelteKit, Spring Boot, Spring WebFlux, Spring Data JPA, Hibernate, Vitest, Jest, Playwright

Practices: Solution Architecture, Event‑driven Architecture, Microservices, Test‑driven Development, CI/CD, DevOps, Code Review, Technical Leadership

Languages spoken: English (fluent), Portuguese (native)