Generative AI Engineer

This is a fully remote position, open to applicants in Texas.

📋 Description

• Design and develop production-quality generative AI systems, including agentic workflows, multi-step RAG pipelines, and applications powered by LLM, integrated with enterprise data and services.

• Establish and implement reusable engineering patterns for prompt management, workflow versioning, structured outputs, tool orchestration, and rollback mechanisms across production AI services.

• Utilize discernment in model selection and routing, optimizing for token usage and latency, managing costs, and defining the right boundaries between AI-driven and deterministic application logic.

• Regularly assess emerging AI models, tools, and architectural strategies, integrating enhancements into existing systems in a gradual manner.

• Connect AI systems with enterprise data sources, internal APIs, and platforms to facilitate dependable, production-ready workflows.

• Take ownership of operational outcomes for production AI systems in terms of reliability, latency, throughput, cost efficiency, and scalability goals.

• Establish and sustain monitoring, observability, tracing, and alerting frameworks to guarantee operational transparency and prompt issue resolution.

• Design and manage CI/CD pipelines for the deployment, versioning, and release management of AI services.

• Lead response efforts for production incidents and conduct root cause analysis, promoting systemic improvements to minimize recurrence.

• Develop and maintain automated evaluation pipelines for LLM outputs, including prompt regression testing, retrieval quality validation, and failure mode tracking.

• Implement controls for human-in-the-loop, content guardrails, schema validation, and structured output enforcement to ensure reliable and auditable AI outputs.

• Protect AI systems against prompt injection, data leakage, and unauthorized access, ensuring alignment with enterprise compliance and security standards.

• Direct the technical strategy for the team's GenAI initiatives, defining and upholding engineering standards, patterns, and best practices across all GenAI workstreams.

• Make and justify architectural decisions clearly, providing the necessary technical rationale for the Manager and stakeholders to align and proceed confidently.

• Collaborate closely with the Manager of GenAI Engineering to receive, refine, and execute scoped GenAI projects, contributing technical insights to prioritization and tradeoff discussions.

• Provide hands-on code review and technical mentorship to engineers involved in GenAI workstreams, enhancing overall quality through direct feedback and demonstration.

• Advocate for an iterative delivery culture, promoting incremental shipping, feedback incorporation, and continuous improvement in a regular production release cycle.

⛳️ Requirements

• Proven experience in delivering production-grade LLM or generative AI systems, including tradeoffs in prompt and workflow design, model selection and routing, tool usage, and the boundaries between AI guardrails and deterministic application logic.

• Proficient in building automated evaluation pipelines for LLM outputs, encompassing gold set construction, model-based evaluation methodologies, prompt regression testing, retrieval quality validation, and failure mode analysis across the full LLM application stack.

• Experience in implementing human-in-the-loop controls, content guardrails, and schema-based output validation for enterprise AI deployments.

• Strong history of designing, developing, and maintaining complex distributed systems in enterprise production settings, with clear accountability for reliability, performance, and operational outcomes.

• Familiarity with CI/CD pipeline design and operation for AI services, including strategies for deployment, versioning, and release management in production settings.

• Demonstrated capability to define and uphold GenAI engineering standards, patterns, and best practices across cross-functional teams.

• Experience in designing and operating cloud-native APIs, microservices, and event-driven architectures on Azure or a similar cloud platform.

• Proficient in integrating AI systems with enterprise data sources, internal APIs, and security controls in compliance-sensitive environments.

• Track record of delivering production AI systems iteratively, maintaining a regular release schedule, incorporating feedback, and fostering continuous improvement.

• Bachelor's degree in Computer Science, Engineering, Data Science, or a related field, or equivalent practical experience.

• Experience in designing and managing agentic AI systems and multi-step RAG architectures in production, focusing on retrieval quality optimization, chunking strategies, grounding, and ranking tradeoffs.

• Practical experience with Azure OpenAI, AI Foundry, App Service, Functions, Service Bus, Blob Storage, Key Vault, and Application Insights; familiarity with Bicep for Infrastructure as Code (IaC).

• Proficient in Python frameworks commonly utilized in production AI services, such as FastAPI, asyncio, and Pydantic.

• Familiarity with PySpark notebooks for developing data pipelines.

• Experience in deploying and managing containerized AI workloads using Docker or similar technologies.

• Understanding of responsible AI principles, AI governance frameworks, and regulatory considerations pertinent to enterprise AI systems.

• Familiarity with Bronze/Silver/Gold medallion architecture and staged data quality patterns for enterprise data pipelines.

• Domain expertise in product data, PIM, ERP, master data management, data governance, ecommerce, or analytics platforms.

• Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.

🏝️ Benefits

• Competitive salary and performance-based incentives.

• Comprehensive health, dental, and vision insurance.

• Flexible working hours and remote work options.

• Opportunities for professional development and continuous learning.

• Collaborative and innovative work environment.