Senior AI Systems Engineer

Lucentive; United States; Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Remote work with EU overlap

Job summary

Lucentive is seeking an experienced engineer to own the shared AI systems layer used by multiple products. You will shape runtime behavior across tools, memory, retrieval, and reasoning and define patterns for provider changes that keep architecture durable as teams and products grow.

You will design and maintain the orchestration runtime, build provider interfaces for flexible model changes, and own regression testing and drift detection.

Qualifications

• Experience building AI systems and production infrastructure used by multiple products or teams.
• Strong software engineering discipline with typed, production-grade implementation.
• Experience designing abstractions that endure provider changes.
• Ability to set technical direction and build infrastructure other engineers can adopt independently.
• Practical evaluation experience with tests that catch regressions and inform release decisions.
• English fluency for engineering collaboration and written review.

Responsibilities

• Design and maintain the orchestration runtime that combines tools, memory, retrieval, and reasoning.
• Create a provider interface that supports model changes or mixed-provider strategies without requiring product-level rewrites.
• Own shared evaluations, including reference data, regression checks, and drift detection.
• Define reusable engineering patterns and decide when engagement-specific pipelines should become shared infrastructure.
• Review architecture choices across projects and keep them aligned as they scale.
• Maintain production observability and turn system contracts into clear interfaces for downstream teams.

Skills

AI systems

Production infrastructure

English fluency

Tools

Next.js

Convex

Job description

Role overview

Own the shared AI systems layer used by multiple products, shaping how tools, memory, retrieval, and multi-step reasoning work together at runtime. The role also sets durable patterns for model-provider changes and evaluation, keeping the architecture reliable as more teams and products build on it.

Responsibilities

• Design and maintain the orchestration runtime that combines tools, memory, retrieval, and reasoning.
• Create a provider interface that supports model changes or mixed-provider strategies without requiring product-level rewrites.
• Own shared evaluations, including reference data, regression checks, and drift detection.
• Define reusable engineering patterns and decide when engagement-specific pipelines should become shared infrastructure.
• Review architecture choices across projects and keep them aligned as they scale.
• Maintain production observability and turn system contracts into clear interfaces for downstream teams.

Requirements

• Experience building AI systems and production infrastructure used by multiple products or teams.
• Strong software engineering discipline, including typed, production-grade implementation; Next.js and Convex or equivalent experience is relevant.
• Experience designing abstractions that remain useful through framework or provider changes.
• Ability to set technical direction and build infrastructure other engineers can adopt independently.
• Practical evaluation experience, with tests that catch regressions and inform release decisions.
• English fluency for engineering collaboration and written review.

Nice to have

• Experience working where AI outputs require evidence or traceability, such as regulated or high-stakes settings.
• Experience keeping prompts and evaluations versioned and reviewed in source control.

Benefits and work setup

• Remote role for an EU-based team, with at least four hours of overlap with CET on working days; a Portugal hub is noted.
• Available as contract or full-time, with start timing coordinated at offer stage.