FLEX Software Engineer, Conversational AI and Intelligent Search

Marriott • Bethesda, MD

1d • $42 - $69

About The Position

The FLEX Software Engineer, Conversational AI and Intelligent Search designs, builds, tests, and operates production-grade conversational AI and intelligent search experiences that deliver accurate, reliable, secure, and personalized customer interactions. The role develops AI agents, retrieval workflows, backend services, APIs, and integrations, applying scalable architecture, structured tool use, evaluation, observability, security, and operational reliability to move generative AI solutions from concept to production. This is a temporary position with an assignment duration through September 11, 2027.

Requirements

• Bachelor's degree in Computer Science, Software Engineering, Information Technology, or a related field, or a high school diploma/GED with an additional 4 years of professional experience.
• At least 2 years of professional software engineering experience.
• Programming experience in Python, Java, JavaScript, TypeScript, or a comparable language.
• Demonstrated experience building and operating production backend services, APIs, cloud-native applications, containers, Kubernetes, distributed systems, and automated CI/CD pipelines.
• Hands-on experience developing generative AI, conversational AI, intelligent search, retrieval-augmented generation, or agent-based applications, including model APIs, prompt engineering, tool calling, structured outputs, embeddings, retrieval, context management, testing, observability, secure development, and sensitive-data handling.

Nice To Haves

• Experience building multi-agent or workflow-orchestrated AI systems using frameworks such as LangChain, LlamaIndex, Semantic Kernel, AutoGen, Temporal, or comparable technologies.
• Experience with vector databases, hybrid search, reranking, retrieval optimization, AI evaluation, LLM-as-judge patterns, experimentation, latency and token optimization, caching, and cost management.
• Experience with responsible AI, prompt-injection defenses, content safety, red-team testing, OpenTelemetry, application-performance monitoring, canary deployments, feature flags, progressive delivery, and localized, accessible, high-traffic customer applications.

Responsibilities

• Design, build, test, deploy, and operate production-grade conversational AI applications, intelligent search experiences, and AI agents.
• Develop multi-turn workflows, agent routing, structured tool calling, memory, and context-management capabilities.
• Build retrieval-augmented generation and intelligent search solutions using embeddings, vector retrieval, hybrid search, reranking, and grounding techniques.
• Integrate AI applications with internal APIs, search platforms, databases, model providers, and external services.
• Develop scalable APIs, streaming interfaces, asynchronous workflows, and event-driven backend services.
• Implement prompt management, model configuration, structured outputs, safety guardrails, authentication, authorization, and secure data-handling practices.
• Improve response accuracy, grounding, relevance, personalization, latency, scalability, and cost efficiency through measurement and iterative engineering.
• Create unit, integration, contract, end-to-end, and automated regression tests for AI applications and supporting services.
• Partner with Quality Engineering to develop evaluation datasets, release-quality thresholds, and repeatable AI evaluation and experimentation practices.
• Implement logging, metrics, distributed tracing, alerting, dashboards, and production diagnostics using OpenTelemetry and application-performance monitoring platforms.
• Troubleshoot complex production issues across models, prompts, application code, infrastructure, data stores, and downstream dependencies, and perform root-cause analysis.
• Participate in architecture reviews, code reviews, release planning, CI/CD implementation, progressive delivery, and production support.
• Evaluate emerging generative AI technologies and make pragmatic architecture and implementation decisions aligned with business, security, reliability, and operational requirements.
• Collaborate across Product, Engineering, Quality Engineering, Security, Platform, and Operations teams to deliver inclusive, accessible, and high-traffic customer experiences.

Benefits

• 401(k) plan
• Stock purchase plan
• Discounts at Marriott properties
• Commuter benefits
• Employee assistance plan
• Childcare discounts
• For full-time positions: medical, dental, vision, health care flexible spending account, dependent care flexible spending account, life insurance, disability insurance, accident insurance, adoption expense reimbursements, and paid parental leave
• For Washington applicants: paid sick leave accrual and eligibility to receive a minimum of 9 holidays annually

What This Job Offers

• Career Level: Mid Level