Boomer Perry

We’re seeking a GenAI Engineer with hands-on experience delivering AWS Bedrock solutions from proof-of-concept through production. You’ll design and implement production-ready GenAI applications, with a strong emphasis on RAG architectures, vector databases, agentic workflows, and safety/guardrails, alongside modern Python engineering and cloud/DevOps best practices. What You’ll Do:

• Design, build, and deploy Generative AI applications using AWS Bedrock and related AWS services
• Implement Retrieval-Augmented Generation (RAG) patterns, including:
  • document ingestion pipelines
  • embedding strategies
  • chunking approaches
  • retrieval tuning and evaluation
• Integrate and manage vector databases (selection, indexing, performance tuning, lifecycle management)
• Build and orchestrate agentic workflows (tool use/function calling, multi-step flows, orchestration patterns)
• Implement guardrails and safety controls (prompt/content filtering, policy enforcement, PII handling, secure prompting, monitoring)
• Develop backend services and pipelines in Python to support AI workflows and integrations
• Leverage AI/ML tooling for evaluation and observability (e.g., Langfuse or similar)
• Collaborate with engineering and stakeholders to translate business needs into technical designs
• Support production readiness via cloud architecture + DevOps: CI/CD, IaC, monitoring/alerting, deployment automation, environment management

Required Qualifications

• Demonstrated AWS Bedrock experience in real implementations (PoC through production)
• Strong understanding of GenAI concepts including:
  • RAG
  • vector databases
  • agent orchestration
  • guardrails / safety controls
• Strong Python development experience (services, APIs, pipelines)
• Experience with AI/ML frameworks and tooling, including Langfuse or similar
• Solid foundation in cloud architecture and DevOps practices supporting production systems

Nice to Have

• Prior experience delivering GenAI solutions in complex enterprise environments
• Experience improving model/app quality via structured evaluation, testing, and monitoring