AI Engineer

We are seeking a Senior AI / Cloud Engineer to lead the development of production-grade, retrieval-augmented generation (RAG) and agent-based systems for a cloud-native enterprise technology platform operating across highly regulated environments. This is a contract position focused on building secure, scalable LLM-powered applications on AWS, with an emphasis on Amazon Bedrock and event-driven architectures. The role is fully remote, supporting U.S.-based teams. Candidates must have deep hands-on experience delivering AI systems into production environments. U.S. work authorization is required. No visa sponsorship is available at this time.

Job Title: Senior AI / Cloud Engineer (LLM & AWS Bedrock)

Location: Remote (U.S.-based only)

Responsibilities

• Design and build RAG-based conversational systems over S3-hosted knowledge bases, including ingestion, parsing, chunking strategies, metadata enrichment, embeddings, indexing, retrieval, reranking, and citation-grounded responses
• Implement and manage Amazon Bedrock integrations, including foundation models, embeddings, and Bedrock Guardrails for PII handling, content safety, prompt-injection mitigation, topic constraints, and safe completions
• Develop agentic workflows using Bedrock Agents / AgentCore and AWS Lambda tools, including allowlisted tool calling, schema validation, approval flows, audit logging, and secure execution patterns
• Engineer AWS-native automation pipelines for knowledge base updates using S3 eventing and orchestration, with resilient processing patterns such as retries, idempotency, and dead-letter queues
• Design and maintain LLM evaluation frameworks and quality gates, including golden datasets, CI/CD regression testing, groundedness and citation validation, retrieval quality metrics, and latency/cost monitoring
• Implement production-grade observability and operational controls, including CloudWatch dashboards and alarms, structured logging and tracing, incident readiness practices, and cost governance

Required Skills & Experience

• 7+ years of professional software engineering experience, with demonstrated delivery of production AI or LLM-based systems on AWS
• Strong Python engineering background with hands-on experience building and operating cloud-native services in production
• Extensive experience across core AWS services, including Amazon Bedrock (foundation models, embeddings, and Guardrails), AWS Lambda, CloudWatch, DynamoDB (schemas and access patterns), and S3 (event-driven ingestion and automation)
• Deep expertise in RAG system design, including chunking strategies, metadata management, hybrid retrieval approaches, reranking, and citation-based response generation
• Hands-on experience with LLM prompting patterns, context management, and hallucination mitigation techniques
• Experience building agent-based systems using Bedrock Agents / AgentCore or equivalent frameworks, with a focus on safe tool use and auditability
• Familiarity with enterprise search and retrieval systems such as Amazon Kendra, OpenSearch, or vector database patterns
• Experience with production delivery tooling, including API Gateway, Step Functions, EventBridge, SQS/SNS, and CI/CD pipelines
• Strong understanding of AWS security and reliability best practices, including IAM least privilege, KMS, Secrets Manager or SSM, CloudTrail, rate limiting, retries, and caching
• Experience with infrastructure as code using Terraform, CloudFormation, or CDK
• AWS Machine Learning Specialty certification or an equivalent, recognized AI/ML certification is required

Compensation

• Hourly Rate: $80 - $90 per hour

Additional Information

• This is a fully remote contract role; candidates must be based in the United States
• Must be authorized to work in the United States — no visa sponsorship available
• Engagement is hands-on and delivery-focused, working closely with engineering and platform stakeholders

For more information or to apply, contact Ryan Dwyer ***email_hidden***