Refer a Friend

About the Client

It's one of the world's largest IT services and consulting companies, which provides end-to-end technology consulting, digital transformation, managed services, cloud, cybersecurity, data & AI, and business process outsourcing to enterprises and public sector organizations worldwide.

You will join a large-scale digital transformation initiative for global enterprise clients, delivering innovative technology solutions that help organizations modernize their operations, accelerate cloud adoption, improve data-driven decision-making, and strengthen cybersecurity. Depending on the assignment, you will work on projects involving cloud platforms, enterprise applications, data & AI, automation, and managed services across a variety of industries.

Your Team

You will become part of an international, multidisciplinary team of experienced engineers, architects, consultants, and delivery professionals who collaborate across general locations. The team embraces knowledge sharing, innovation, and continuous improvement, working closely with clients to solve complex business challenges while maintaining high standards of technical excellence, collaboration, and customer success.

What's in it for you

- Interview process that respects people and their time
- Professional and open IT community
- Internal meet‑ups and resources for knowledge sharing
- Time for recovery and relaxation
- Bright online and offline events
- Opportunity to become part of our internal volunteer community

Responsibilities

- Design and implement end-to-end Generative AI solutions using Amazon Bedrock and Amazon SageMaker.




- Build and deploy AI Agents and multi‑agent workflows using Amazon Bedrock Agents.
- Develop RAG architectures using Bedrock Knowledge Bases, embeddings, vector databases, and enterprise data sources.
- Fine‑tune, evaluate, and deploy models using Amazon SageMaker.
- Design and implement document ingestion pipelines, metadata extraction, and enterprise search capabilities.
- Develop validation frameworks to assess response quality, groundedness, hallucinations, citations, and agent performance.
- Configure Amazon Bedrock Guardrails and implement Responsible AI and governance controls.
- Implement monitoring and observability using Amazon CloudWatch, SageMaker Model Monitor, and related AWS services.
- Monitor model performance, latency, cost, drift, and operational metrics.
- Deploy GenAI workloads using SageMaker Endpoints, Lambda, ECS/EKS, API Gateway, and Step Functions.
- Build CI/CD and MLOps pipelines using SageMaker Pipelines, GitHub Actions, AWS CodePipeline, and Terraform.
- Integrate AI solutions with enterprise platforms such as SharePoint, APIs, and business applications.
- Lead POCs, architecture reviews, technical assessments, and knowledge transfer activities.

Skills

Required Skills

Generative AI

- RAG architectures, embeddings, retrieval optimization, and vector search.
- AI Agents,



agent orchestration, tool calling, and workflow automation.
- Prompt engineering, model evaluation, hallucination detection, and response validation.

AWS GenAI Stack

- Amazon Bedrock (Agents, Knowledge Bases, Guardrails, Foundation Models).
- AWS Lambda, API Gateway, Step Functions, ECS/EKS.

Data & Search

- OpenSearch, PostgreSQL/pgvector, Redis, Pinecone, or similar vector databases.
- OCR, document processing, metadata enrichment, and enterprise search.

Monitoring & Governance

- AI observability, model monitoring, drift detection, and performance analysis.
- Responsible AI, NIST AI RMF, security, and governance frameworks.

DevOps & Cloud

- CI/CD, MLOps, Terraform, GitHub Actions, Kubernetes, and Docker.

Required Certifications

- AWS Certified Solutions Architect – Associate or Professional

Preferred Certifications

- Azure Solutions Architect (AZ-305)

Desired Experience

- Building production‑grade AI Agents using Amazon Bedrock.
- Implementing Bedrock Knowledge Bases and enterprise RAG solutions.
- Fine‑tuning and deploying models with Amazon SageMaker.
- Establishing evaluation, monitoring, and governance frameworks for GenAI applications.
- Deploying scalable AI solutions in AWS production environments.

I am informed about the processing of my personal data and the right to withdraw my consent. By submitting the completed “Contact Us” form, your personal data will be processed by Brightgrove. All the information on how we store and use the data you can find in our “Privacy Policy”. Which are written in human language.

#J-18808-Ljbffr

📌 Architect GenAI Software Engineer Medellin, Colombia, Remote (Medellín)
🏢 Brightgrove
📍 Medellín