Sr. AI Software Engineer (Compute Test, North Reading)

Teradyne•North Reading, MA

1d•$161,700 - $258,800

About The Position

Teradyne’s AI Ops team is building knowledge and retrieval infrastructure that helps engineering teams use AI agents and developer tools across a large technical codebase and documentation set. As a Senior AI Software Engineer, you will help evolve an existing proof of concept into an owned, reliable, and measurable platform. This senior individual-contributor role sets technical direction for the retrieval platform while remaining hands-on in design, implementation, testing, and operation. You will work independently on complex technical problems, evaluate tradeoffs, and collaborate across engineering disciplines.

Requirements

Production experience building and operating backend or platform systems, with the ability to take technical ownership and contribute hands-on.
Experience with search, code intelligence, or retrieval-augmented generation (RAG), including architecture, failure modes, operational tradeoffs, and retrieval-quality measurement.
Strong Python and systems engineering skills for designing and debugging services, pipelines, indexing, APIs, tests, and operational tools.
Knowledge of lexical and vector retrieval, re-ranking, chunking, freshness and invalidation, and techniques for finding relevant evidence in documents and code.
Ability to evaluate retrieval with representative questions and labeled evidence, distinguish retrieval performance from generated-answer quality, and use error analysis to guide decisions.
Ability to become effective in unfamiliar codebases and engineering domains; prior semiconductor-test experience is not required.
Clear cross-functional communication skills and the ability to share technical context through documentation, runbooks, and engineering patterns.
Experience using AI-assisted development tools productively and verifying generated code through testing, review, and evidence.

Responsibilities

Lead the technical direction, design, implementation, testing, and operation of the retrieval platform.
Develop Python services and pipelines that index source repositories and engineering documents while preserving permissions.
Build repeatable evaluations for lexical and vector search, ranking, chunking, freshness, and code- and document-aware retrieval.
Collaborate with partner teams that own source systems and access rules to deliver practical API and MCP-compatible integrations.
Ensure operational health is visible through measures for index freshness, failures, retrieval quality, latency, and relevant cost.
Support platform adoption through hands-on code, tests, operational tooling, documentation, and shared engineering patterns.