[Hiring] Generative AI Solution Engineer @Leidos

Role Description

Leidos is seeking an experienced Generative AI Solution Engineer to design, deliver, and operate AI-enabled customer service for the HUD FHA Resource Center. The selected candidate will lead implementation of AI self-service and agent assistance for voice and chat that is grounded in approved HUD content, protected by guardrails, and hands off smoothly to customer service representatives. The ideal candidate has taken generative AI from pilot to production in a customer-facing setting, knows when to configure a platform’s built-in AI capabilities and when a custom build is justified, and can produce the evidence that federal AI governance and security reviews require.

This is an exciting opportunity to work with emerging AI technologies, solve complex technical challenges, and make a meaningful impact while supporting a federal customer.

Please Note: 100% Remote | Candidate must reside within reasonable commuting distance of the Washington, DC metropolitan area in the Washington, DC / Gaithersburg, MD Metro Area.

Core Responsibilities

• Design, configure, and deploy AI agents for customer self-service on voice and chat, including their instructions, tools, and escalation behavior.
• Develop Retrieval-Augmented Generation from approved program content, and work with content owners to keep the knowledge base accurate and current.
• Implement prompt engineering, topic routing, and safe escalation to a live representative when AI is not the right answer, with a fallback path that keeps every customer reachable.
• Configure AI guardrails for PII redaction, prompt-injection detection, denied topics, and content safety.
• Build contact-center flows, bots, and serverless functions that connect AI agents to customer channels, backend systems, and transfer to a live representative.
• Carry conversation context across voice and chat and into the live-agent handoff, and deliver AI assistance for customer service representatives, such as suggested answers and contact summaries.
• Integrate AI capabilities with the contact-center platform and the customer relationship management (CRM) system, with secure logging, encryption, and least-privilege access.
• Lead AI testing, response quality tuning, grounding validation, and latency optimization across production-like scenarios, including multilingual and adversarial (red-team) testing against the OWASP Top 10 for LLM Applications.
• Define and run ongoing AI quality evaluation (accuracy, grounding, safety, and resolution of the customer’s need), and use the results to tune prompts, content, and guardrails.
• Produce the documentation that federal AI governance and security authorization require. Work with the ISSO on NIST SP 800-53 controls and privacy reviews, and support HUD’s AI use-case inventory under OMB M-25-21.
• Manage AI agent, prompt, guardrail, and flow configuration as code, released through government change control.

Qualifications

• Bachelor’s degree and 8+ years of software engineering or cloud development experience.
• At least 3 years of Generative AI or LLM application development experience.
• Delivered at least one customer-facing generative AI solution from pilot to production, with measurable results (for example, resolution rate, answer accuracy, or customer satisfaction).
• Strong software development skills (for example, Python) and experience building production cloud solutions, preferably on AWS.
• Hands-on experience building AI agents, RAG patterns, and vector-based retrieval on a cloud contact-center, CRM, or generative AI platform (for example, Amazon Connect or Amazon Bedrock).
• Experience with APIs, distributed systems, and secure cloud architecture.
• Ability to work effectively in a regulated government environment, including working with security staff on NIST SP 800-53 control documentation for the systems the candidate builds.
• U.S. Citizen.
• Ability to obtain and maintain a Public Trust security clearance.

Preferred Qualifications

• AWS certifications such as Generative AI Developer – Professional, Machine Learning Engineer – Associate, AI Practitioner, Security – Specialty, or Solutions Architect – Professional, or equivalent contact-center or CRM platform AI certifications.
• Experience with contact-center AI features such as AI agents, agent assistance, conversation analytics, and automated quality evaluation.
• Experience evaluating and selecting foundation models on accuracy, latency, cost, and FedRAMP authorization status.
• Familiarity with FedRAMP environments and government AI governance requirements, such as OMB M-25-21, the NIST AI Risk Management Framework and its Generative AI Profile (NIST AI 600-1).
• Experience with Amazon Bedrock Agents, AgentCore, LangChain, Strands Agents, or other agent development frameworks, and with the Model Context Protocol (MCP).
• Experience with CRM platforms such as Salesforce Service Cloud, including their native AI agent and agent-assist features.
• Experience migrating a contact center between platforms, and with multilingual voice and chat bots.
• Ability to explain AI risks, tradeoffs, and results clearly to program leaders, security reviewers, and non-technical stakeholders.

Additional Notes

This is a 100% telework/remote opportunity. However, candidates must reside within reasonable commuting distance of the Washington, DC metropolitan area in the Washington, DC / Gaithersburg, MD Metro Area.

Please be advised that during the interview, you will be required to keep your camera on, and your interviewer will be taking your picture for identification purposes if an offer letter is extended to you.

The anticipated program salary budget for this role is approximately $130,000 to low/mid $150,000 with limited flexibility based on qualifications and assessment (no guarantees). Final compensation will be determined based on relevant experience, responsibilities, internal equity, market data, and applicable requirements.