Senior AI Application Engineer

InterSystems•Boston, MA

12h•$137,000 - $212,000

About The Position

Join InterSystems’ Managed Services team to build and operate production AI applications that improve the deployment, patching, upgrading, migration, and support of InterSystems solutions across AWS, Google Cloud, Azure, and on-premises environments. The role applies agentic AI, LLM-powered tooling, and modern software engineering practices to operational challenges, reducing manual effort, preventing errors, improving deployment quality, and validating upgrades and migrations. The engineer will collaborate across teams to mature prototypes into secure, reliable, supportable production solutions for healthcare and other regulated environments. Success is measured by reducing manual operational effort, improving deployment quality, accelerating migrations, and increasing service reliability through practical applications of AI.

Requirements

At least 8 years of professional software engineering experience building, deploying, and supporting production systems.
Strong Python skills and working knowledge of technologies such as Bash, ObjectScript, Go, Java, or similar languages.
Demonstrated experience designing, deploying, and supporting production AI applications beyond coursework, hackathons, personal projects, prototypes, or demonstrations.
Hands-on experience applying LLMs and AI technologies to engineering or operational problems, including APIs, agent frameworks, RAG, vector databases, guardrails, memory systems, evaluation frameworks, and model monitoring.
Experience delivering measurable business or operational outcomes through AI, such as reducing manual effort, improving accuracy, accelerating delivery, or increasing service reliability.
Experience building reliable production validation, testing, automation, or operational frameworks with error handling, reporting, and maintainable integration with real systems.
Experience supporting production deployments, upgrades, migrations, patching, monitoring, incident response, reliability, or cloud operations across AWS, Google Cloud, Azure, and on-premises environments.
Docker, Kubernetes, CI/CD, and Infrastructure-as-Code experience with Terraform, CloudFormation, Pulumi, or similar tools.
Strong understanding of security, data privacy, and software engineering best practices, with the judgment to apply them to AI-enabled solutions for sensitive and regulated environments such as healthcare.
Strong communication and problem-solving skills, including the ability to translate operational challenges into scalable automation.
Ability to discuss contributions to a production AI application, including its architecture, evaluation, security controls, support model, and measurable outcomes.

Nice To Haves

Background in cloud migrations, patch management, release automation, or platform modernization.
Experience integrating commercial or open-source foundation models into production AI applications.
Open-source contributions in AI, cloud, automation, or software engineering.
Experience in regulated industries, including healthcare, life sciences, financial services, or government.
Familiarity with AI-assisted development tools such as GitHub Copilot, Claude Code, Cursor, Tabnine, Replit, or equivalents.

Responsibilities

Build AI-powered automation for deployments, patching, upgrades, migrations, and operational workflows across cloud and on-premises environments.
Build production validation harnesses for deployments and migrations, including automated testing, configuration drift and anomaly detection, and post-deployment checks against real systems.
Apply LLMs, retrieval-augmented generation (RAG), agentic AI frameworks, and related technologies to improve operational efficiency and deployment reliability.
Design AI solutions with security, data privacy, reliability, and safety as first-class requirements for healthcare and other regulated customer environments.
Define pre-production evaluation criteria for AI solution accuracy, safety, reliability, and operational effectiveness.
Design monitoring and observability mechanisms for AI-enabled solutions, including performance, reliability, operational impact, and cost visibility.
Evaluate and integrate AI-assisted development tools, agent platforms, and automation technologies into CI/CD, testing, and operational workflows.
Build internal tooling initiatives that measurably reduce manual operational work and can be matured into supportable production solutions.
Partner with cross-functional teams to integrate AI-driven practices into production workflows and drive adoption.
Stay current with emerging AI technologies and identify practical opportunities to apply them to Managed Services operations.