Full-stack engineer with 8+ years shipping consumer-scale products at high-growth companies. Experienced in AI-native product engineering, distributed systems, and real-time collaboration.
work
stack
writing
now
◉ Ocala → Remote
● Open to opportunities
8+ yrs shipping
LEAD ENGINEER · AI SYSTEMS
Lead software engineer focused on building consumer-scale applications and high-impact AI features. I've spent eight years shipping across the stack—from core backend services and real-time collaboration tools to RAG pipelines and LLM orchestration.
in production
users served
growth supported
AI assets generated
~/alejandro — zsh
$ whoami
lead_software_engineer
$ ls ~/focus/
ai-systems/ full-stack/
recommendations/ distributed-systems/
$ cat ./principles.txt
→ end-to-end product ownership
→ data-driven feature iteration
→ systems designed for scale
$ █
CURRENTLY SHIPPING
AI-native workspace tooling.
// 01 — PHILOSOPHY
I believe the best software is built at the intersection of robust backend infrastructure and intuitive user experiences. My goal is to build products that not only scale to millions of users but also provide genuinely helpful, personalized assistance through AI.
I prioritize clean abstractions and data-backed decision-making. Whether it's optimizing recommendation models or refining a real-time collaborative canvas, I focus on the metrics that define success for the end user and ensure the architecture is built to last.
full-stack development
AI/LLM pipelines
recommendation systems
distributed services
technical leadership
// 02 — STACK & TOOLING
A versatile toolkit built for scaling complex applications from prototype to global production.
⟨/⟩
TypeScript for cohesive full-stack web development. Python for AI/ML pipeline orchestration and data processing. Go for high-performance backend services.
TypeScript
Python
Go
Java
SQL
◈
Kubernetes and Docker for scalable containerization. AWS/GCP for robust cloud architecture. Terraform for infrastructure as code, ensuring repeatable environments.
Kubernetes
AWS/GCP
Docker
PostgreSQL
Terraform
✦
RAG pipeline development and vector search optimization. LLM routing and prompt orchestration. Experience with feature stores and model serving frameworks.
RAG
Vector Search
LLM Routing
FastAPI
Redis
◐
Comprehensive monitoring with Prometheus and Grafana. Deep insight into LLM performance using OpenTelemetry, tracking latency, token usage, and quality scores.
Prometheus
Grafana
OpenTelemetry
A/B Testing
// 03 — SELECTED WORK
Core projects from my tenure at high-growth companies that demonstrate my focus on product engineering and AI integration.
PROJECT 01
LUMINA AI
Real-time AI Document Editor
Led the development of a real-time collaborative canvas integrated with multi-agent AI systems. Managed the RAG pipeline for Q&A, significantly reducing hallucinations and latency through intelligent model routing.
34% lift
Session length
28% reduction
Hallucination rate
$48K/mo
Cloud cost savings
// router/inference.ts
async function routeModel(prompt: string) {
const complexity = estimate(prompt);
if (complexity < threshold) {
return provider.fast(prompt);
}
return provider.complex(prompt);
}
[ARCHITECTURE]
users →
canvas
→
agents
→
vector-db
↓
llm-router
←
evals
→
observability
→ reduced p99 latency by 50% via routing
PROJECT 02
SPOTIFY
Natural language discovery
Owned the end-to-end integration for natural language playlist creation. Scaled the personalization service to serve 100M+ users and successfully integrated recommendation models that boosted engagement.
Java
ML Models
Kafka
BigQuery
PROJECT 03
AIRBNB
Core booking & host tooling
Engineered core backend services supporting massive marketplace growth. Redesigned the bookings pipeline to enhance system reliability and improved critical host tools, significantly increasing user engagement.
→
Reliable checkout pipeline for global users
→
Smart Pricing & host performance insights
→
Rapid pivot to virtual event infrastructure
IMPACT METRICS
Booking growth
3.2x over 2 yrs
320%
Error reduction
4.1% → 1.8%
−56%
Host response
18% increase
18%
// 04 — EXPERIENCE
Eight years of professional software engineering spanning AI-native startups, music streaming, and marketplace giants.
2024
—
2026
Lead Software Engineer
·
SAN FRANCISCO
Led a team of four to build an AI-native document editor. Owned roadmap and architecture, shipping features used by 85,000+ users monthly. Established team engineering practices and improved incident response.
Team Leadership
AI Architecture
Product Strategy
System Design
2021
—
2023
Senior Software Engineer
·
REMOTE
Developed backend and full-stack features for Home and Discover feeds. Scaled personalization services and shipped the AI Playlist feature. Contributed to ranking model improvements impacting 180M+ users.
Recommendation Engines
Full-stack Systems
Team Leadership
2018
—
2021
Software Engineer
·
San Francisco, CA
Developed core backend services for the Airbnb Experiences marketplace (booking, availability calendar, host payouts) that supported 3.2× growth in Experiences bookings over 2 years.
Booking
Availability Calendar
ML Infrastructure
// 05 — IMPACT
Key achievements from building and scaling products at Airbnb, Spotify, and Lumina AI. I prioritize measurable improvements to user experience and infrastructure efficiency.
SESSION LENGTH
Lift achieved at Lumina AI after launching the real-time Collaborative Canvas and AI agent features.
DEPLOYMENT SPEED
Reduced model deployment cycles at Spotify from three weeks to two days by modernizing the serving stack.
ANSWER QUALITY
Improvement in RAG pipeline accuracy for Workspace Q&A after implementing a rigorous evaluation framework.
BOOKING GROWTH
Supported massive expansion of the Airbnb Experiences marketplace through backend core service development.
OPERATIONAL EXCELLENCE
Established new incident response playbooks and design review culture at Lumina AI, resulting in a 45% improvement in team MTTR and a more robust, collaborative development cycle.
45%
FASTER MTTR
// 06 — OPEN SOURCE
While my primary work is proprietary, I actively maintain and contribute to tools that improve engineering developer productivity.
chavez/eval-tools
★ 120
A lightweight evaluation framework for LLM-based applications, designed to run prompt A/B tests with high reliability.
Python
MIT
chavez/metrics-exporter
★ 45
Custom observability exporter for tracking LLM token costs and latency, integrated with standard monitoring stacks.
TypeScript
MIT
chavez/router-kit
★ 80
Infrastructure utility for routing traffic between multiple AI models to optimize for both latency and cost.
Go
MIT
// 07 — WRITING & TALKS
Reflections on building large-scale products, implementing AI features, and fostering team growth in fast-paced environments.
ESSAY · 2026
Lessons learned from productionizing RAG pipelines and managing multi-model routing at scale.
ARTICLE · 2025
Technical breakdown of using CRDTs to maintain consistency in multi-user document editing environments.
ESSAY · 2024
My approach to owning features end-to-end, from early architecture to post-launch product optimization.
TALK · TECHCONF '24
Experiences from Airbnb regarding ranking experiments and improving user conversion through infrastructure tuning.
// 08 — CREDENTIALS
B
University of Florida
2017
S
Professional Development
2018 — Present
★
8+ years professional experience
CONTINUOUS LEARNING
◇
Mentored 3+ engineers to senior roles
2024
// 09 — KIND WORDS
I value building strong relationships with cross-functional teams. Here is what former leads and peers have noted about our work together.
"
Alejandro is the rare engineer who balances deep technical design with a relentless focus on product outcomes. He owned our architecture reviews and kept our team aligned during periods of rapid growth.
TL
Team Lead
Lumina AI
"
He managed the migration of our recommendation stack with zero downtime, showing immense technical maturity. His ability to explain complex ML pipeline tradeoffs to stakeholders was a major asset for us.
EM
Eng Manager
Spotify
"
Alejandro mentored me from junior to senior. He is rigorous about code quality and system architecture, but always makes time to support team members. He sets the bar for professional growth.
SE
Software Engineer
Airbnb
// 10 — NOW
What I am prioritizing in my professional development and projects right now.
BUILDING
Developing a personal boilerplate for fast-tracking RAG-based AI workspace applications.
READING
Advanced system design patterns and research on multi-agent LLM task orchestration.
ADVISING
Helping early-stage teams think through scalable frontend and backend infrastructure.
AWAY FROM
Deep dives into low-level LLM optimizations—I need a weekend off from prompt engineering.
// 11 — CONTACT
Open to senior full-stack and lead engineering roles where I can contribute to product growth and team mentorship. Reach out to connect.
>
© 2026 Alejandro Chavez · Ocala, FL
built with care · deployed to production