AI Engineer (AWS Bedrock / Agentic AI / Python / Golang)
Location:
Remote (LATAM)
Employment Type:
Contract (Long-Term)
About the Role
We are looking for a highly skilled
AI Engineer
to design and develop next-generation Generative AI applications using the AWS AI ecosystem. You will build intelligent AI agents, evaluation frameworks, and scalable backend services that power enterprise-grade AI solutions.
This role is ideal for engineers who enjoy working with
LLMs, AI Agents, Retrieval-Augmented Generation (RAG), prompt engineering, and AI evaluation
while building production-ready applications.
Responsibilities
- Design, develop, and deploy Generative AI applications using
Amazon Bedrock
.
- Build intelligent AI agents using
AWS AgentCore
and
AWS Strands
.
- Develop scalable backend APIs and microservices using
Python
and
Go (Golang)
.
- Build Retrieval-Augmented Generation (RAG) pipelines.
- Design prompt engineering and prompt optimization strategies.
- Develop AI evaluation frameworks including:
- LLM-as-a-Judge
- Human-in-the-Loop evaluation
- Prompt evaluation
- Model benchmarking
- Implement automated testing and quality assurance for AI applications.
- Work with vector databases and embedding models.
- Collaborate with product managers, architects, and engineering teams to deliver enterprise AI solutions.
- Optimize AI applications for performance, reliability, scalability, and cost.
Required Qualifications
- 5+ years of software engineering experience.
- Strong Python development experience.
- Experience with
Go (Golang)
.
- Hands-on experience with
Amazon Bedrock
.
- Experience building Generative AI applications using LLMs.
- Experience with AI Agents and agentic workflows.
- Experience developing REST APIs and backend services.
- Strong understanding of prompt engineering.
- Experience with Git and CI/CD.
Preferred Qualifications
Experience with one or more of the following:
- AWS AgentCore
- AWS Strands
- LangChain
- LangGraph
- MCP (Model Context Protocol)
- Vector databases (OpenSearch, Pinecone, Weaviate, Chroma, FAISS)
- Knowledge graphs
- AI evaluation tools such as:
- DeepEval
- Ragas
- Promptfoo
- TruLens
- LangSmith
- LLM-as-a-Judge methodologies
- Human evaluation and calibration frameworks
- Prompt evaluation and benchmarking
- AWS Lambda
- ECS/EKS
- Docker
- Kubernetes
- Terraform
Nice to Have
- AI testing and quality engineering experience.
- Experience building AI copilots or AI assistants.
- Experience with observability and monitoring for AI applications.
- Experience working with enterprise-scale cloud environments.
Technologies
- Amazon Bedrock
- AWS AgentCore
- AWS Strands
- Python
- Go (Golang)
- LangChain
- LangGraph
- MCP
- Vector Databases
- Docker
- Kubernetes
- REST APIs
- Git
- CI/CD
What You'll Work On
You will be part of a team building enterprise AI solutions that leverage Large Language Models, intelligent AI agents, retrieval systems, and advanced evaluation frameworks to deliver secure, scalable, and production-ready AI applications for enterprise customers.