Juan Manuel Ciro

Building intelligent systems at scale

>

Staff-level AI/ML Engineer with +9 years of experience building large-scale ML systems, agentic platforms, and production AI infrastructure. Co-author of 16 papers across NeurIPS, ICML, ACL, and Nature.

InputContextAgentsOutputs
User InputMulti-modal
OrchestratorAgent Router
MemoryLong-term
KnowledgeRAG · Vectors
Code AgentGeneration
ResearchWeb · APIs
VisionImage Analysis
ReasoningChain of Thought
TextStreaming
CodeExecutable
ImagesGenerated
DataStructured
ActionsTool Calls
scroll

+9 yrs

Engineering Experience

200K+

Monthly Requests Handled

16

Research Publications

99.98%

System Reliability

about.ts
1const juan = {
2role: "Technical Lead / Staff AI Engineer",
3location: "Medellin, Colombia",
4stack: [
5"React", "Next.js", "TypeScript", "Python",
6"PyTorch", "Temporal", "Kubernetes", "LLMs"
7],
8publications: [
9"NeurIPS (Best Paper)", "ICML", "ACL", "Nature"
10],
11reliability: 99.98,
12monthlyRequests: 200_000,
13ships: true
14}

Career

Professional Experience

+9 years of experience building production ML systems, from early-stage startups to industry-defining platforms.

Depth by Domain

Technical Expertise

Agentic AI Platforms

At Contextual AI, I lead the Agent Composer team -- designing modular, graph-based agent frameworks that convert RAG pipelines into scalable, observable distributed systems.

Architecture

Domain-Driven Design with composable agent workflows enabling scalable composition across research, sales, and applied teams.

Orchestration

Temporal-based orchestration improving evaluation success from 60% to 98% with 10x throughput scaling.

Observability

Distributed logging, tracing, and metrics reducing MTTR and enabling data-driven reliability engineering.

Temporal.ioDDDGraphQLgRPCDockerK8s

Toolkit

Skills & Technologies

Programming

PythonJavaScriptTypeScriptReactNext.jsNode.js

Distributed Systems & Infra

Temporal.ioDockerKubernetesGCPAWSTerraform

AI / ML

LLM SystemsRAGAgentic WorkflowsNLPComputer VisionML Infrastructure

Observability

GrafanaKibanaDistributed TracingMetricsReliability Engineering