Remote GenAI Engineer

Role Overview

GenAI Engineer responsible for hands-on technical delivery of production generative AI systems, from architecture and implementation through deployment, operations, and continuous improvement. This role covers the full stack of modern GenAI engineering and establishes technical standards for GenAI work across the team.

Key Responsibilities

AI Architecture & Delivery

• Design and build production-grade generative AI systems including agentic workflows, multi-step RAG pipelines, and LLM-powered applications
• Integrate AI systems with enterprise data sources, internal APIs, and cloud-native services
• Define and implement reusable engineering patterns for prompt management, workflow versioning, structured outputs, and tool orchestration
• Apply judgment on model selection, routing, token/latency optimization, and cost management
• Continuously evaluate and incorporate emerging AI models, tools, and architectural approaches

Reliability, Performance & Operations

• Own operational outcomes for production AI systems including reliability, latency, throughput, cost efficiency, and scalability
• Implement monitoring, observability, tracing, and alerting frameworks
• Design and maintain CI/CD pipelines for deployment, versioning, and release management
• Lead production incident response and root cause analysis

Governance, Security & Responsible AI

• Build automated evaluation pipelines for LLM outputs including prompt regression testing and failure mode tracking
• Implement human-in-the-loop controls, content guardrails, and schema validation
• Secure AI systems against prompt injection, data leakage, and unauthorized access
• Ensure compliance with enterprise security and governance standards

Technical Authority & Collaboration

• Own GenAI technical direction and define engineering standards across workstreams
• Make and defend architectural decisions with clear technical rationale
• Provide hands-on code review and technical guidance to team members
• Work closely with management on prioritization and execution of GenAI work

Requirements

• Deep, demonstrable production GenAI experience - hands-on track record building and operating LLM applications at scale
• Strong operational ownership mindset and technical credibility
• Expertise in LLM application design, agentic workflows, and RAG patterns
• Experience with evaluation frameworks, structured outputs, and production safeguards
• Knowledge of cloud-native services and enterprise system integration
• US Citizen or Green Card holder only

Nice-to-Haves

• Experience with prompt engineering and management tooling
• Background in MLOps or production ML systems
• Familiarity with multiple LLM providers and model families