Senior AWS Generative AI Solution Engineer

This is a fully remote position, open to applicants in District of Columbia, +1 more state.

📋 Description

• Design and develop Amazon Bedrock Agents, which consist of a Supervisor Agent and specialized Sub-Agents.

• Create Retrieval-Augmented Generation workflows utilizing Amazon Bedrock Knowledge Bases and OpenSearch Serverless.

• Execute prompt engineering, agent routing, confidence logic, and low-confidence fallback mechanisms.

• Set up Bedrock Guardrails for PII redaction, prompt-injection detection, restricted topics, content safety, and grounding evaluation.

• Construct Lambda orchestration that connects Lex V2, Bedrock AgentCore, response generation, and human transfer decisions.

• Assist with session management, conversation context persistence, and maintaining consistency across voice and chat channels.

• Integrate the GenAI stack with services like Amazon Connect, Salesforce, CloudWatch, DynamoDB, S3, SNS, IAM, and KMS.

• Oversee AI testing, response quality tuning, grounding validation, and latency optimization in production-like scenarios.

• Implement and evaluate Supervisor Agent and Sub-Agents across various HUD service domains.

• Guarantee that responses are grounded, precise, and properly filtered through Guardrails.

• Aid in confidence scoring and fallback strategies for dependable human escalation.

• Deliver a production-ready, sustainable, secure, and privacy-compliant GenAI platform.

⛳️ Requirements

• Bachelor’s degree with 8+ years of relevant experience OR a Master’s degree with 6+ years of relevant experience.

• Additional years of relevant experience may be considered and/or accepted in place of a degree.

• At least 8 years of experience in software engineering or cloud development.

• Minimum of 3 years of experience in Generative AI or LLM application development.

• Proficient in Python development with experience in building production AWS solutions.

• Practical experience with Amazon Bedrock, RAG patterns, and vector-based retrieval.

• Familiarity with APIs, distributed systems, and secure cloud architecture.

• Capability to work effectively within a regulated government environment.

• Eligible to obtain and maintain a Public Trust security clearance.

• Must be a US Citizen.

• Preferred AWS certifications include AI Practitioner, Machine Learning Specialty, or Solutions Architect Professional.

• Experience with Amazon Bedrock Agents, AgentCore Runtime, Guardrails, and Knowledge Bases is preferred.

• Familiarity with Claude models, agent frameworks, or multi-agent orchestration patterns is preferred.

• Knowledge of FedRAMP environments and government AI governance requirements is preferred.

• Experience with LangChain, Strands Agents, or other agent development frameworks is preferred.

• Must reside in or be willing to relocate to the Gaithersburg, MD/Washington, DC metro area.

🏝️ Benefits

• Competitive compensation.

• Health and wellness programs.

• Income protection.

• Paid leave.

• Retirement plans.