Iñaqui Paladino
ML & AI Systems Engineer
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, turning research ideas into reliable, scalable services that teams can actually depend on.
I build with end-to-end product ownership. For mission-critical systems, my design philosophy prioritizes zero-data-loss architecture, idempotency, comprehensive observability, and cost-efficient compute utilization.
Experience
AI Engineer
- ❯ Architected and deployed a production Recommender System for the Reviewer Assignment Problem across 27K+ researchers and millions of scientific papers, leveraging Hybrid Search (Dense + Sparse) via Qdrant.
- ❯ Engineered graph-based Conflict-of-Interest (COI) logic using closure tables in PostgreSQL, automating downstream transformations and data validation suites with dbt.
- ❯ Built distributed, high-concurrency ETL pipelines for data ingestion, crawling, and Entity Resolution across heterogeneous sources (Apache Solr, MySQL, PostgreSQL).
- ❯ Accelerated Bi-Encoder inference (+140% throughput, -60% VRAM) via ONNX Runtime (IOBinding) and Cross-Encoder/Reranker throughput (9x speedup, +6M pairs/run) through vectorized forward passes, dynamic token truncation, and Mixed Precision (FP16) on multi-GPU Tensor Cores.
- ❯ Deployed distributed vLLM-based model serving with dynamic node registration and load balancing; packaged gateway and inference nodes as multi-stage Docker images with multi-vendor GPU support (TensorRT, ROCm).
- ❯ Architected a Multi-Agent system using LangGraph, implementing stateful Router patterns, specialized subgraphs, dynamic tool calling, and prompt management.
- ❯ Engineered production Agentic RAG pipelines featuring Self-Correction (query rewriting, relevance check, adaptive retries) and Multi-Level Memory (dynamic trimming, proactive summarization) to maintain low latency over extended contexts.
- ❯ Standardized workflow orchestration and fault-tolerant pipelines with Prefect, implementing atomic task design, decoupled execution, and automated fallback to local/ephemeral compute.
- ❯ Centralized Experiment Tracking, Model Registry, and Telemetry via MLflow; implemented LLM-as-Judge evaluation with custom metrics and synthetic test sets, integrated with automated CI/CD on GitLab.
Software Engineer
- ❯ Brought in to solve a concrete operational problem: manual bank receipt processing was consuming ~5 hours of an admin's workday. Diagnosed the existing workflow, identified failure points under concurrency, and designed an end-to-end serverless, event-driven solution on AWS.
- ❯ Implemented the pipeline on SQS, S3, Lambda, and DynamoDB with multi-layer idempotent processing (locks), conditional writes, state correlation, and DLQ retries, ensuring accounting integrity and zero 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).
- ❯ Architected and implemented an end-to-end observability strategy using AWS Powertools and CloudWatch (structured logging, custom metrics, and multi-level P1-P3 alarms). 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.
Machine Learning Intern
- ❯ Built an AI-based web platform to support Study and Research Paths (SRP) in the classroom, integrating an unsupervised NLP pipeline that automatically clusters student-generated questions by topic and generates post-class reports for teachers.
- ❯ Designed the clustering pipeline (multilingual SBERT embeddings → cosine-similarity deduplication → UMAP → K-Means with automatic K selection via Calinski-Harabasz), selected through systematic EDA evaluating and discarding Gap Statistics and elbow/silhouette methods; validated against human-annotated ground truth on a real multilingual dataset.
- ❯ Deployed the platform (Astro SSR / Bun / TypeScript + async Python microservice / Docker) in a real classroom pilot and co-authored a scientific publication at CITAD 8 (Barcelona).
Education & Certifications
Professional Certifications
NVIDIA Certified Associate: Generative AI LLMs (NCA-GENL)
- ❯ Official validation of competencies in LLM architectures, RAG (Retrieval-Augmented Generation), fine-tuning, model evaluation, and deployment of generative models on NVIDIA infrastructure.
AWS Certified Solutions Architect - Associate (SAA-C03)
- ❯ Designing resilient, high-performance, secure, and cost-optimized cloud architectures on AWS. Proven expertise in distributed services, serverless patterns (Lambda, SQS, DynamoDB, S3), and Infrastructure as Code with Terraform.
Academic Background
Systems Engineer
- ❯ Distinction: Graduated with academic honors for excellence in engineering coursework.
- ❯ Overall average GPA: 8.75.
- ❯ Intermediate degree: University Programmer Analyst (APU).
Fundamentals of Software Engineering
- ❯ PILA Virtual Program 2023 (Undergraduate academic exchange).
- ❯ Final passing grade: 9.4.
Projects
Financial conversational agent for market analysis on X. Orchestrated with LangGraph featuring a Corrective RAG (CRAG) loop and hybrid search on Qdrant, integrated with an asynchronous event-driven ingestion pipeline. Deployed on Amazon Bedrock AgentCore with real-time streaming (AG-UI), persistent memory on DynamoDB, Terraform IaC, and end-to-end hardening with Cognito auth, WAF protection, and rate limiting.
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.
