AI Engineer

SCIGON; Chicago (IL); On-site; USD 72,000 - 96,000; Full time

Job summary

SCIGON in Chicago, IL is seeking an Applied AI Engineer to design, deploy, and operationalize enterprise AI capabilities. This onsite role will help implement LLM-powered solutions with governance, security, and integration into existing systems, turning AI enablement into reliable production capabilities for business teams.

You will own the end-to-end lifecycle of AI enablement, configure foundation models, and ensure scalable, auditable deployments across security and compliance requirements

Qualifications

• Proven experience developing, publishing, and managing Claude Skills or plug-ins in a production environment.
• Demonstrated success deploying AI capabilities that are actively used by business stakeholders.
• Experience building and deploying solutions in regulated or highly governed enterprise environments.
• Strong understanding of security controls, compliance requirements, access management, and operational governance.
• Comfort working within structured delivery processes and change-control frameworks.
• Strong communication and stakeholder management skills across technical and non-technical audiences.
• Ability to translate business challenges into practical AI-enabled solutions.
• 5+ years in software engineering, automation engineering, or a related technical discipline.
• At least 2 years designing and deploying production-grade LLM-powered solutions.
• Strong proficiency in Python and API-based integrations.
• Experience with enterprise integration patterns and distributed systems.
• Solid engineering practices including testing, source control, observability, monitoring, and supportability.
• Hands-on experience with modern LLM ecosystems, including prompt engineering, model configuration, tool integration, and function execution.
• Experience working in public cloud environments such as Azure, Google Cloud Platform, Vertex AI, or equivalents.
• Ability to evaluate AI use cases pragmatically and determine when traditional engineering approaches may be more effective.
• Self-directed, able to independently lead technical initiatives in a fast-moving environment.

Responsibilities

• Design, deploy, and manage reusable AI capabilities within enterprise AI platforms, including skills, tools, and plug-in functionality.
• Own the end-to-end lifecycle of AI enablement solutions, from intake and configuration through deployment, governance, ongoing support, and optimization.
• Configure and apply foundation models such as Claude, Gemini, and similar technologies to support enterprise automation and business workflows.
• Deliver solutions from concept to production implementation with scalability, security, and operational readiness in mind.
• Integrate enterprise systems, services, and approved tools using available connectivity frameworks and protocols.
• Collaborate with Security, Cloud, and Infrastructure teams to implement access controls, identity management practices, and credential governance.
• Ensure compliance with AI governance standards, including auditability, monitoring, risk controls, and operational guardrails.
• Work across engineering, automation, data, and business teams to identify opportunities and deliver AI-driven capabilities that create measurable impact.

Skills

Claude Skills

LLM ecosystems

Python

API integrations

security controls

change-control

distributed systems

production-grade

stakeholder management

regulatory environments

Tools

Azure

Google Cloud Platform

Vertex AI

Job description

SCIGON is seeking an Applied AI Engineer to design, deploy, and operationalize enterprise AI capabilities. In this onsite role in Chicago, IL, you will help implement LLM-powered solutions with enterprise governance, security, and integration into existing systems, turning AI enablement into reliable production capabilities for business teams.

What you’ll work on

• Design, deploy, and manage reusable AI capabilities within enterprise AI platforms, including skills, tools, and plug-in functionality.
• Own the end-to-end lifecycle of AI enablement solutions, from intake and configuration through deployment, governance, ongoing support, and optimization.
• Configure and apply foundation models such as Claude, Gemini, and similar technologies to support enterprise automation and business workflows.
• Deliver solutions from concept to production implementation with scalability, security, and operational readiness in mind.
• Integrate enterprise systems, services, and approved tools using available connectivity frameworks and protocols.
• Collaborate with Security, Cloud, and Infrastructure teams to implement access controls, identity management practices, and credential governance.
• Ensure compliance with AI governance standards, including auditability, monitoring, risk controls, and operational guardrails.
• Work across engineering, automation, data, and business teams to identify opportunities and deliver AI-driven capabilities that create measurable impact.

Key requirements

• Proven experience developing, publishing, and managing Claude Skills or plug-ins in a production environment.
• Demonstrated success deploying AI capabilities that are actively used by business stakeholders.
• Ability to contribute quickly with minimal onboarding and ramp-up time.
• Experience building and deploying solutions in regulated or highly governed enterprise environments.
• Strong understanding of security controls, compliance requirements, access management, and operational governance.
• Comfort working within structured delivery processes and change-control frameworks.
• Strong communication and stakeholder management skills across technical and non-technical audiences.
• Ability to translate business challenges into practical AI-enabled solutions.
• 5+ years in software engineering, automation engineering, or a related technical discipline.
• At least 2 years designing and deploying production-grade LLM-powered solutions.
• Strong proficiency in Python and API-based integrations.
• Experience with enterprise integration patterns and distributed systems.
• Solid engineering practices including testing, source control, observability, monitoring, and supportability.
• Hands-on experience with modern LLM ecosystems, including prompt engineering, model configuration, tool integration, and function execution.
• Experience working in public cloud environments such as Azure, Google Cloud Platform, Vertex AI, or equivalents.
• Ability to evaluate AI use cases pragmatically and determine when traditional engineering approaches may be more effective.
• Self-directed, able to independently lead technical initiatives in a fast-moving environment.

Technologies you may use

Claude, Gemini, Python, Azure, Google Cloud Platform, Vertex AI, LLM ecosystems, Model Context Protocol (MCP), RAG architectures, vector databases, embeddings, semantic search solutions, RBAC

Preferred qualifications

• Experience building AI agents and multi-agent workflows.
• Familiarity with orchestration platforms and agent frameworks.
• Understanding of Model Context Protocol (MCP) implementations and agent-to-agent integrations.
• Experience with RAG architectures, vector databases, embeddings, and semantic search solutions.
• Knowledge of modern identity and access management concepts, including RBAC, service accounts, agent identities, and least-privilege models.
• Previous experience supporting organizations in highly regulated industries such as insurance, financial services, healthcare, or similar sectors.

Compensation: USD 52 - 70 per hour.