Software Engineer - AI Systems (Go)

Stanbridge University•Irvine, CA

1d•Remote

About The Position

Stanbridge University is seeking a Software Engineer to design, build, deploy, and operate production AI systems that perform complex, multi-stage work reliably at scale. This hands-on role focuses on long-running workflows that use models, tools, and external APIs; preserve state; generate structured content and media; incorporate human review; recover from failures; and deliver accurate results. The work involves distributed-systems and production-engineering challenges beyond prompt development, including provider failures, rate limits, interrupted workflows, changing state, non-deterministic model behavior, output correctness, variable latency and cost, and deployments while work is in progress. The engineer will help design substantial portions of the University's AI architecture and will own patterns, services, infrastructure, and engineering standards. Work includes Go-based APIs and backend services, durable workflow orchestration, multi-provider model infrastructure, agent and tool orchestration, prompt versioning and testing, evaluation and regression systems, quality controls, human-in-the-loop workflows, generated-media pipelines, observability, and secure ingestion of untrusted documents. Engineers may emphasize either platform and pipeline engineering—distributed systems, orchestration, durable state, reliability, scalability, and cost—or agents and quality—agent architecture, prompts, context, evaluation, evidence validation, and output quality. Specialization is not required. This position is eligible for remote work only for candidates residing in states where Stanbridge University is authorized to employ remote employees; candidates must reside in an eligible state at the time of employment. Compensation depends on education, experience, qualifications, and internal equity. A job-related assessment may be required during the interview process. Applicants must be authorized to work in the United States; the University does not provide employment-based immigration sponsorship. Employment offers are contingent on a background check, and official transcripts are required before hire.

Requirements

Substantial professional experience developing and operating production software.
Strong experience with Go (Golang), or demonstrated depth in another backend language and ability to become productive in Go quickly.
Hands-on experience shipping an LLM-backed application, AI agent, or agent-based system into production and supporting it after deployment.
Strong understanding of AI application architecture and interactions among models, agents, tools, APIs, data sources, services, and application logic.
Demonstrated distributed-systems knowledge, including concurrency, asynchronous processing, queues, idempotency, retries, partial failure, state management, and recovery.
Experience designing systems that remain reliable when services, providers, or workflow stages fail.
Demonstrated testing discipline for systems involving non-deterministic behavior.
Strong experience designing and consuming HTTP APIs.
Experience with relational databases, SQL, and persistent application state.
Experience building, deploying, monitoring, and troubleshooting backend services in production environments.
Understanding of software architecture, testing, debugging, observability, and production-engineering practices.
Ability to independently own ambiguous technical problems from investigation through production implementation.
Strong analytical judgment and ability to balance reliability, quality, performance, complexity, and cost.
Must be legally authorized to work in the United States; the University does not provide employment-based immigration sponsorship.
Must provide official transcripts prior to hire; degrees earned outside the United States must be evaluated by a recognized credential evaluation service for U.S. degree equivalency and applicable subject-area coursework.
Must be able to perform each essential duty satisfactorily and be physically present in the office unless otherwise noted.
Candidates seeking remote work must reside in an eligible state at the time of employment.

Nice To Haves

Experience with AI agent frameworks, orchestration patterns, or custom agent architectures, including understanding when a framework may not be appropriate.
Experience with retrieval-augmented generation (RAG), embeddings, vector databases, semantic search, or knowledge-retrieval architectures.
Experience developing evaluation and observability systems for LLM applications, including tracing, regression suites, quality dashboards, or automated evaluation.
Experience with judge models, structured-output validation, evidence checking, or other AI quality-control mechanisms.
Experience designing human-in-the-loop workflows involving review, approval, intervention, or modification of active workflow state.
Experience with document processing, headless-browser rendering, text-to-speech, image generation, video generation, or other media pipelines.
Experience with event-driven architectures, durable job queues, and asynchronous processing at scale.
Experience with containers, cloud infrastructure, CI/CD, and production deployment environments.
Understanding of prompt injection, authorization boundaries, data isolation, and security considerations when processing untrusted content with AI systems.
Experience developing systems where generated-output accuracy has operational, regulatory, compliance, or safety implications.

Responsibilities

Design, develop, test, deploy, and operate production-quality software and backend services, primarily using Go.
Architect and build AI agents and agent-based systems that use tools, interact with APIs, maintain state and context, and execute complex multi-step workflows.
Design durable workflows that checkpoint, resume, retry, recover, and safely continue after partial failures or interruptions.
Determine how models, agents, tools, APIs, data sources, services, and deterministic application logic should divide responsibilities, including when an AI model is not appropriate.
Design integrations across AI model providers, including routing, failover, rate-limit management, health monitoring, and degradation strategies.
Build safeguards such as structured-output validation, error handling, retries, quality gates, evidence validation, and automated recovery.
Develop testing strategies for non-deterministic AI behavior using deterministic fixtures, recorded and replayed interactions, regression suites, evaluation harnesses, and quality baselines.
Develop observability through tracing, metrics, logging, evaluation data, and replayable execution histories.
Design human-in-the-loop workflows for review, approval, intervention, and modification of workflow state.
Build and maintain APIs, backend services, relational data models, job-processing infrastructure, and supporting application components.
Develop secure methods for ingesting and processing user-supplied documents and external content.
Optimize systems for reliability, latency, throughput, scalability, output quality, and cost per execution.
Build reusable engineering patterns and shared components for adding agents, model providers, tools, workflows, and output types.
Own technical problems from investigation and architecture through implementation, deployment, monitoring, troubleshooting, and ongoing production operation.
Collaborate with product stakeholders and domain experts to translate qualitative requirements into measurable system behavior and technical solutions.
Contribute to architectural decisions and engineering standards for AI-powered applications across the University.