Colombia
Published on: October 1, 2026
Colombia (Remote) | Full-time | 1 Opening
🚀 Build the data and AI backbone of a platform at scale, with real ownership and fully remote from Colombia.
ABOUT OUR CLIENT
Our client is an AI-powered enterprise platform that automates end-to-end recruitment and workflow orchestration. Their platform runs at production scale, coordinating complex third-party integrations, processing large volumes of unstructured data, and running real-time, event-driven pipelines across multiple systems.
THE OPPORTUNITY
We're looking for a Senior Back-End Engineer, based in Colombia and working fully remote, to own microservices, data pipelines, and the agents stack. You'll build systems that take large volumes of raw, semi-structured, and unstructured data and turn them into clean structured records and search indices that power agent workflows and the core platform. You'll join a small, high-ownership team where engineers drive decisions from pipeline architecture to cloud infrastructure, design systems together, and ship independently without heavy process.
WHAT YOU'LL DO
Design and operate high-throughput data pipelines in Python (FastAPI) that ingest, validate, and normalize large-scale data feeds
Build extraction, parsing, and enrichment workflows that turn raw files into structured, searchable records
Design and maintain Elasticsearch / OpenSearch indices, from schema design to bulk ingestion and retrieval optimization
Develop agent execution runtimes and tool-calling interfaces, including state, context limits, persistence, and streaming
Integrate with GraphQL APIs, internal services, and external vendor APIs with solid error handling and rate limiting
Build resilient event-driven systems on AWS (SQS, ECS, S3, RDS) with idempotency, retries, and dead-letter handling
Profile and debug live pipelines to keep them fast, reliable, and accurate under uneven workloads
WHAT YOU BRING
Deep, production-grade experience with Python and FastAPI, including async services and clean API contracts
Hands-on experience building pipelines that process large volumes of messy or semi-structured data at scale
Practical experience with Elasticsearch or OpenSearch (index design, mappings, bulk indexing, query optimization)
Practical GraphQL experience, including schemas, mutations, and cross-service API contracts
Strong working knowledge of AWS (ECS, SQS, S3, RDS) and deploying containerized services in production
PostgreSQL or equivalent, plus async ORMs such as SQLAlchemy
Experience with message queues (SQS, Kafka, or similar), retry strategies, idempotency, and dead-letter queues
Ability to turn ambiguous requirements into resilient designs without close supervision
Comfort using logs, traces, metrics, and database profiling to diagnose live issues
NICE TO HAVE
Experience with LLM APIs and agent workflows (LangGraph, LangChain, LiteLLM, structured outputs, tool calling)
Familiarity with TypeScript and Node.js / NestJS
Parsing complex documents (PDF, DOCX, large spreadsheets, JSON exports)
Infrastructure-as-code (AWS CDK, Terraform, or similar)
Workflow orchestration frameworks (Inngest, Temporal, or similar)
HOW YOU WORK
You explain your design decisions clearly in writing, so others can follow your reasoning without a call
You bring a considered position to design reviews and change it when a better argument comes along
You give and receive direct, specific feedback on code and designs without defensiveness
You question complexity before adding it and favor the simplest solution that works
This posting may involve the use of AI tools to assist in reviewing applications; final hiring decisions are made by humans.
As part of our hiring process, this role may use Keystone AI’s artificial intelligence or automated tools to assist with reviewing and screening applications. These tools support, but do not replace, human judgment in making hiring decisions.
Your application will be considered complete only after you have completed the full registration process on the Keystone AI platform, including creating your profile, uploading your CV, and submitting your application. The AI interview is optional but encouraged and is not required for your application to be considered.
By submitting your personal data and/or resume, you give consent to collection, use and disclosure of your personal data and/or resume by the company (or its agent) for the purpose of the processing and administration by the company relating to this job application. Read our Privacy Policy.
CGP Group is an affirmative equal-opportunity employer and recruitment firm. We evaluate qualified applicants without regard to race, color, religion, creed, gender, sexual orientation, gender identity, marital status, national origin, age, veteran status, disability, or any other protected class. Information provided in this advertisement is for recruitment purposes only.