Senior Software AI Engineer - Fullstack
United States
Full-time
3 days ago
$114,000 - $182,000 USD
H1B Sponsor Likely
Key skills
PythonAWSAgentic AI architecturesInfrastructure as CodeGitHub ActionsTypeScriptReact/Next.jsSRE foundationsAI development toolsRelational databasesSoft skillsSwiftKotlinAIMLLangChainLangGraphReactNext.jsTerraformLambdaS3CloudWatchPostgreSQLMySQLOracleGitHubiOSAndroidCI/CD
About this role
Southern New Hampshire University is a team of innovators looking for an experienced Senior AI Engineer, Platform (full stack). The role involves engineering backend systems for an AI learning platform, designing agent orchestration, and ensuring production readiness while collaborating on product delivery.
Responsibilities:
- You will design and implement scalable APIs/services for developing AI agents, including orchestration, memory, tool use, and learner interaction
- You will implement rigorous evaluation frameworks to improve agent performance (offline and in-product), and build the instrumentation to make results actionable improvement cycles
- You will build data flows/pipelines that allow real-time personalization and learning insights
- You will ensure data quality and accessibility for training and evaluating learning agents
- You will improve developer velocity with solid API design, testing practices, and realistic architecture choices
- You will ship end-to-end product slices: implement backend capabilities and the corresponding lightweight web UI (and occasionally mobile) to unblock product progress
- You will build lightweight internal tools/admin surfaces for evaluation, debugging, content/ops workflows, and product iteration
- You will collaborate with product/design to deliver high-quality user experiences while keeping scope and maintainability sane
- You will help establish the basics of production readiness: monitoring, dashboards, logging/tracing, and performance/cost hygiene
- You will contribute to automated testing and deployment pipelines for rapid, safe iteration (CI/CD, rollbacks, environment hygiene)
- You will participate in incident response when needed and help shape runbooks, postmortems, and an on-call model appropriate for our current stage
Requirements:
- 5+ years production Python experience at scale (or equivalent)
- AWS expertise (Lambda, S3, and CloudWatch)
- Familiarity with compound systems combining LLMs, ML, and traditional software components
- Experience with agentic AI architectures (e.g., CrewAI, LangGraph/LangChain, AutoGen, LlamaIndex, MCP, A2A, ACP, DSPy, or custom frameworks)
- Hands-on experience with evaluation methodologies for LLMs and agent-based AI systems
- Infrastructure as Code experience (CDK, Terraform, or similar)
- GitHub Actions or similar CI/CD platforms
- Experience communicating updates and resolutions to customers and other partners
- Comfortable working across the stack when needed. Read and write TypeScript, and ship small UI features using React/Next.js or similar technologies. Additionally, the ability to contribute occasional mobile changes in iOS/Swift and Android/Kotlin
- Experience building production readiness / SRE foundations (instrumentation/observability basics, safe deployments, performance/cost hygiene)
- Active user of AI development tools (GitHub Copilot, Cursor, Claude Code, Codex) with personal projects and evolution over the past 12 months
- Demonstrated examples of AI-augmented productivity gains
- Enthusiasm for pushing boundaries of AI-assisted engineering
- Experience with a relational database such as MySQL, PostgreSQL, or Oracle