FREE ACCESS
5,000–10,000 jobs/day
See all jobs on JobTailor
Search thousands of fresh jobs every day.
Discover
- Fresh listings
- Fast filters
- No subscription required
Create a free account and start exploring right away.
Tech Stack
Tools & technologiesAWSDynamoDBRayTerraform
About the role
Key responsibilities & impact- Design and implement multi-agent AI architectures using AWS Bedrock
- Develop agent orchestration logic and collaborative agent workflows
- Configure and manage AWS Bedrock Agents, Knowledge Bases, and Guardrails
- Build Retrieval-Augmented Generation (RAG) pipelines using vector databases and embeddings
- Implement tool integrations using Model Context Protocol (MCP) and API-based services
- Optimize LLM behavior through prompt engineering, tuning, and context management
- Develop observability and monitoring strategies for AI workflows using CloudWatch and X-Ray
- Build scalable event-driven architectures and resilient integration patterns
- Design error handling, retry strategies, and graceful degradation mechanisms
- Collaborate with engineering, product, and architecture teams to deliver production-grade AI solutions
- Support infrastructure automation and deployment pipelines using IaC and CI/CD practices
- Ensure governance, security, auditability, and compliance standards across AI systems
Requirements
What you’ll need- Proven experience building production AI/ML systems on AWS
- Strong hands-on expertise with AWS Bedrock Agents (AgentCore)
- Experience designing multi-agent systems and agent orchestration workflows
- Experience with AWS Bedrock Knowledge Bases (RAG), vector embeddings, and OpenSearch Serverless
- Expertise with AWS Bedrock Guardrails, including PII protection and content governance
- Experience implementing tool calling, function invocation, and state management
- Strong prompt engineering and LLM optimization experience
- Deep understanding of AWS observability tools: CloudWatch, X-Ray, Distributed tracing
- Experience with: API Gateway, DynamoDB, Event-driven architectures
- Familiarity with Infrastructure as Code: Terraform, AWS CDK
- Strong knowledge of RESTful APIs and integration patterns
- Experience with CI/CD pipelines for ML and AI systems
- Ability to design resilient and fault-tolerant AI applications
- Strong communication, collaboration, and technical documentation skills
- Nice to Have: Experience with Model Context Protocol (MCP)
- Experience with AWS Step Functions for workflow orchestration
- Familiarity with: CloudFront, S3, AWS WAF
- Knowledge of conversational AI UX patterns and hybrid interaction models
- Experience with session persistence and conversation state management
- Understanding of compliance and governance requirements: PII handling, Audit trails, Data retention
- Experience optimizing AWS Bedrock and OpenSearch operational costs
- Familiarity with LLM evaluation frameworks and AI quality metrics
- Experience with multi-turn dialogue management and context preservation
- Knowledge of explainability and AI reasoning visualization techniques
Benefits
Comp & perks- Health and dental insurance
- Meal and food allowance
- Childcare assistance
- Extended paternity leave
- Partnership with gyms and health and wellness professionals via Wellhub (Gympass) TotalPass;
- Profit Sharing and Results Participation (PLR);
- Life insurance
- Continuous learning platform (CI&T University);
- Discount club
- Free online platform dedicated to physical, mental, and overall well-being
- Pregnancy and responsible parenting course
- Partnerships with online learning platforms
- Language learning platform
- And many more!
ATS Keywords
✓ Tailor your resumeApplicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard Skills & Tools
multi-agent AI architecturesagent orchestrationAWS BedrockRetrieval-Augmented Generation (RAG)prompt engineeringLLM optimizationInfrastructure as Code (IaC)CI/CD practicesAPI-based servicesvector databases
Soft Skills
communicationcollaborationtechnical documentationdesign resilienceerror handlinggraceful degradationmonitoring strategiesteam collaborationproblem-solvingadaptability