Software Engineering SMTS / LMTS, AI Core

What you'll do

• Design, build, and operate retrieval systems using RAG and hybrid search to provide agents with accurate context.
• Own the end-to-end delivery of AI initiatives from initial scoping and design through launch and monitoring.
• Build developer tooling and frameworks for multi-agent orchestration, prompt management, tracing, and evaluation.
• Diagnose and resolve issues with answer quality by separating retrieval problems from generation problems.
• Define data models for ingesting and segmenting content from documents, knowledge bases, and call transcripts.
• Implement evaluation, observability, and rollout practices to ensure AI changes are safe to ship.
• Set and track performance benchmarks for retrieval, indexing, and LLM provider usage across the platform.
• Manage operational health by participating in on-call rotations and leading incident resolution for owned systems.

What we're looking for

• Proven experience shipping production AI or backend systems in high-ownership environments with a focus on LLM-powered applications.
• Expertise building retrieval systems using RAG and hybrid search, including chunking, indexing, embeddings, and reranking.
• Expertise building developer tooling for production agents, including multi-agent orchestration, registries, and tracing infrastructure.
• Experience owning platform initiatives from design through adoption for retrieval, indexing, and LLM provider integrations.
• Demonstrated technical leadership in designing solutions for non-trivial problems and influencing architecture beyond immediate workstreams.
• Strong backend engineering fundamentals in Ruby on Rails, Python, JavaScript, or Go with SQL and RDBMS experience (PostgreSQL preferred).
• Hands-on experience with the AI application lifecycle, including dataset curation, offline/online evaluation, and error analysis.
• Experience with pgvector, query performance at scale, or processing conversation transcripts (preferred).