About Me
Hi! I'm Iñaqui Paladino Bravo, I'm 24 years old and I'm from Tandil, Buenos Aires, Argentina.
I design and implement AI systems for production. I work at the intersection of software engineering and model behavior, combining deep technical expertise in NLP (embeddings, RAG, reranking) with cloud-native architectures on AWS.
I focus on developing end-to-end solutions: from designing semantic pipelines and optimizing latency in multi-GPU inference, to orchestrating vector databases and deploying serverless event-driven systems (IaC with Terraform).
I build systems taking full ownership of the product. In critical environments where errors are costly, I prioritize resilience: "no-loss-first" approaches, idempotency, and end-to-end observability.
I am looking to join high-performing teams where the daily standard is solving complex problems at scale.
Experience
Software Engineer (Python & AWS)
- • Designed and implemented a serverless, event-driven pipeline on AWS for document processing, eliminating ~5 daily hours of manual data entry and ensuring end-to-end integrity in a production environment.
- • Implemented an asynchronous flow with SQS, S3, Lambda, and DynamoDB using multi-layer idempotent processing (locks), conditional writes, state correlation, and DLQ retries, avoiding duplicates and data loss under concurrency.
- • Adopted a no-loss-first approach with explicit trade-offs between false negatives and positives, reinforced by deterministic validations and business rules, prioritizing accounting integrity in a critical system.
- • Integrated Amazon Textract (OCR) with deterministic extraction and validation logic, plus business rules to ensure transactional integrity and structured data extraction.
- • Secured public endpoints with HMAC-SHA256 signature verification and managed all infrastructure as code with Terraform (remote state, least-privilege IAM, SSM, environment-based parametrization).
- • I implemented an end-to-end observability strategy using AWS Powertools and CloudWatch (structured logging, custom metrics, and multi-level P1–P3 alarms). I automated dashboard provisioning through Terraform, creating an Operational dashboard for infrastructure telemetry (concurrency management, idempotency, and OCR error rates) and an Executive dashboard focused on business KPIs and reliability trends.
AI Engineer
- • Built a semantic analysis engine on top of the second-largest public database in the country (CONICET/SIGEVA): indexing 27k+ researchers and millions of scientific publications for semantic search, automated profiling, and intelligent assignment via multi-language NLP.
- • Developed recommendation systems to identify scientific evaluation experts, using a two-stage matching pipeline (bi-encoder + cross-encoder) that maximizes semantic affinity while respecting institutional constraints. Embeddings are stored and queried in Qdrant, implementing hybrid search that combines dense vectors (semantic similarity) and sparse vectors (BM42 via FastEmbed, for exact lexical matches).
- • Optimized the cross-encoder reranker with manual forward passes and mixed precision (FP16 + autocast), achieving a ~9x speedup by leveraging Tensor Cores (CUDA) and multi-GPU parallelism. Resolved dependency conflicts between PyTorch, onnxruntime, and ROCm to make the pipeline portable across two environments (CUDA and ROCm), including conflicting CUDA/HIP libraries.
- • Built a PoC researcher-search engine for industry demands: identifies the most relevant experts for a given technical problem in seconds.
- • Designed concurrent ETL pipelines to unify heterogeneous legacy repositories (Apache Solr, MySQL, PostgreSQL), developing Entity Resolution and deterministic deduplication algorithms to consolidate millions of records without collisions.
- • Orchestrated MLOps infrastructure with real-time language detection, caching strategies, and model/database deployment via Docker and CI/CD pipelines (GitLab).
Software Developer
- • Designed, developed, and implemented a fullstack educational web platform to support Study and Research Paths (SRP), an inquiry-based didactic approach that promotes collaborative and meaningful learning in mathematics.
- • Developed the platform’s core architecture using Astro SSR on Bun, and integrated an asynchronous Python worker for on-demand generation of analytical classroom reports.
- • Implemented role-based authentication (teachers and students), file storage, and real-time collaboration and tracking capabilities.
- • Designed and implemented an Applied ML pipeline for automated educational data analysis. Built a semantic clustering system using Sentence Transformers (SBERT) for embedding generation, UMAP for dimensionality reduction, and K-Means for clustering, enabling the identification of hidden patterns in student responses and the assessment of learning progress.
- • Deployed the platform in a real-world classroom pilot with teachers and students, validating its adoption in context.
- • Co-authored a scientific paper presenting the pilot results at an international didactics conference in Barcelona.
Systems Engineer
- • Intermediate degree: University Programmer Analyst
- • Distinction: Graduated with academic honors
- • Overall average: 8.75
AWS Solutions Architect Associate (SAA-C03)
Fundamentals of Software Engineering
- • PILA Virtual Program 2023 (Academic exchange)
- • Final grade: 9.4
Projects
Autonomous Agent featuring reasoning capabilities and a RAG pipeline. Orchestrated with LangChain and persistent memory to maintain conversational context. Its 100% automated architecture (Terraform) is highly decoupled: a pay-per-use Serverless AWS API interacts with a dynamic filtering interface and an ephemeral Qdrant vector database, resulting in a cost-optimized and easily extensible product.
Virtual financial analyst built on AWS Serverless architecture. It monitors and analyzes the market on X (formerly Twitter) via a fully decoupled, event-driven workflow. The infrastructure is defined entirely with Terraform (IaC). Orchestration is managed by EventBridge, which triggers ephemeral tasks on ECS Fargate Spot for robust data extraction (handling real sessions and evasion techniques), followed by asynchronous processing on Lambda utilizing Large Language Models (LLMs) for contextual report generation. The frontend operates on a Git-based CMS model: every report triggers a GitHub Actions pipeline that deploys the static site globally via CloudFront.
Serverless solution for ephemeral and secure file transfer on AWS. It includes a CLI to generate temporary upload and download links using S3 Pre-Signed URLs, wrapped in disposable HTML interfaces, with no persistent backend. The infrastructure is fully defined using Terraform (IaC), leveraging remote state and execution via IAM AssumeRole in a multi-account environment, where the Route53 Hosted Zone, the Terraform backend, and ACM certificate validation reside in the management account (AWS Organization). Perimeter security is ensured through CloudFront with Origin Access Control (OAC), keeping the buckets strictly private with TLS/SSL termination.
Fork of the official AWS Labs serverless Dynamic DNS solution for Route53. On top of the original baseline, I added production-oriented improvements for real routers and legacy devices: a DynDNS-compatible endpoint (/nic/update), HTTP/HTTPS support via CloudFront, Basic Auth and temporary token-based authentication for browser updates.
Web-based classroom-style platform designed to support teaching through Study and Research Paths (SRPs), organizing learning around questions and answers. It enables real-time collaboration, academic progress tracking, and automatic analysis of educational data using AI techniques. It is currently used by teachers and students in real classroom contexts, and its development led to a scientific publication presented at an international conference on didactics.
User: usuario@demo.com Password: password
Personal Cloud Infrastructure
Setup and maintenance of a self-hosted cloud infrastructure on a VPS (DigitalOcean), used to deploy and monitor multiple personal apps with Coolify. Includes a private VPN (WireGuard) for secure device communication, a self-hosted S3 server (MinIO) with access control and expiring links, and a N8N instance to orchestrate complex workflows. Also features advanced configuration of firewall, DNS, custom domains, reverse proxy, and SSL certificates.
