Senior AI Engineer, AWS Bedrock

Automat-it

. Build and deliver production-ready GenAI systems on AWS, including Amazon Bedrock, AgentCore, RAG systems, intelligent document processing, voice AI, and LLM-powered services .

Posted 10/15/2026full-timeMadrid • SpainSeniorWebsite

Tech Stack

Tools & technologies

AWSDockerDynamoDBKubernetesPythonTerraform

About the role

Key responsibilities & impact

Build and deliver production-ready GenAI systems on AWS, including Amazon Bedrock, AgentCore, RAG systems, intelligent document processing, voice AI, and LLM-powered services
Design and implement AI agents using Amazon Bedrock AgentCore, AWS Strands, MCP, and modern orchestration frameworks for real customer solutions
Work closely with Solution Architects, DevOps, and customer teams to turn discovery workshops, ideas, and POCs into production-ready AI systems
Evaluate and select appropriate LLMs based on accuracy, latency, cost, and customer requirements
Build reusable AI components and deployment patterns for future customer projects
Deploy, monitor, and improve ML/LLM systems in production, focusing on performance, cost, and reliability
Work with AWS services including Bedrock, OpenSearch, Lambda, S3, DynamoDB, SageMaker, and CloudWatch
Adapt existing ML or GenAI code into production environments
Continuously improve system quality, including retrieval performance, output consistency, and evaluation approaches
Own projects as the main engineer in a fast-paced, project-based environment

Requirements

What you’ll need

Strong hands-on experience building and deploying AI / GenAI systems in production
Strong hands-on AWS experience beyond model invocation, including infrastructure, IAM, serverless services, networking, storage, monitoring, and production deployments using Amazon Bedrock
Experience building RAG systems in practice, including retrieval logic, vector databases, and output quality improvements
Strong understanding of modern LLM ecosystems, including commercial and open-source models, their trade-offs, deployment options, and production use cases
Strong Python skills and a good understanding of backend system design
Experience designing multi-agent systems or more complex orchestration workflows
Experience with vector databases (OpenSearch, pgVector, Pinecone, etc.)
Comfort working in fast-moving environments with short project cycles (weeks to a few months)
Strong communication skills and ability to work directly with clients and cross-functional teams
Ability to clearly explain technical decisions, limitations, and trade-offs in English (written and spoken)
Hands-on experience with Amazon Bedrock Knowledge Bases, AgentCore, Agents, AWS Strands, or MCP is a strong advantage
Experience selecting, evaluating and optimizing LLMs for quality, latency and cost
Experience with Infrastructure as Code (Terraform, CloudFormation or AWS CDK), Docker, Kubernetes and CI/CD pipelines is a strong advantage
Experience with speech-to-text, text-to-speech or Voice AI is an advantage
Background in Machine Learning or Data Science, including model training or fine-tuning, is an advantage