Sr. Applied AI Engineer

We are hiring a Senior Applied AI Engineer to design and build reusable AI systems that accelerate innovation across the organization. This is a senior individual contributor role focused on rapidly prototyping LLM and agent-based workflows, architecting clean and reusable patterns, and partnering closely with our specialty data science team and Head of AI. 

You will translate strategy and ideas into structured, modular systems that can be handed off to production engineering teams or integrated via well-defined APIs.  

We expect end-to-end ownership, pragmatic tradeoffs, and a bias for action. 

Key Responsibilities 

AI Prototyping & Workflow Development 

• Design and build end-to-end LLM-powered workflows, including RAG pipelines, tool-calling systems, and agent architectures 

• Rapidly prototype internal AI assistants and automation tools across business functions 

• Integrate data science models into agent-based workflows 

• Translate ambiguous ideas into practical, working systems 

Reusable Architecture & Enablement 

• Develop shared connectors to major LLM providers and internal data sources 

• Create reusable agent templates and AI development patterns 

• Design modular systems with clean API boundaries for production handoff 

• Implement lightweight evaluation, logging, and tracing patterns appropriate for internal deployment 

Cross-Functional Collaboration 

• Partner deeply with specialty data science teams to operationalize models 

• Work closely with the Head of AI to shape technical direction and AI strategy 

• Communicate architectural decisions and tradeoffs clearly to technical and non-technical stakeholders 

Qualifications 

Education 

• BS in Computer Science, Engineering, Mathematics, or related field required; MS/PhD preferred but not required if experience demonstrates equivalent capability. 

Technical & professional experience  

• 6+ years of professional software or machine learning engineering experience building backend or distributed systems 

• Strong proficiency in Python, including experience building modular, testable, and well-structured codebases.  

• Proficiency in SQL expected, including intermediate querying and basic ETL jobs 

• Hands-on experience developing LLM-powered applications, including RAG pipelines, prompt orchestration, structured outputs, and tool-calling workflows 

• Experience working with vector databases and designing retrieval strategies 

• Experience designing and exposing RESTful or event-driven APIs for internal or external consumption 

• Familiarity with agent frameworks or orchestration libraries (e.g., LangChain, LlamaIndex, Semantic Kernel, or similar) 

• Experience integrating ML or statistical model outputs into production-oriented systems 

• Understanding of evaluation concepts for LLM systems (prompt versioning, offline evals, feedback loops, or guardrails) 

• Comfortable operating in ambiguity and driving initiatives end-to-end with minimal oversight 

Preferred  

• Worked in rapid prototyping and deployment ecosystems 

• Experience building internal AI tooling, SDKs, or developer enablement frameworks 

• Familiarity with cloud environments (AWS preferred), containerization (Docker), and basic deployment patterns 

• Experience working with streaming or ETL pipelines for ingesting structured and unstructured data 

• Exposure to observability practices (logging, tracing, metrics) in application systems 

• Experience handing off prototypes to production engineering teams in a clean, scalable manner 

#LI-REMOTE