Principal AI Engineer - Nexus Black

IFS•Itasca, IL

1d•Hybrid

About The Position

We are seeking a Principal AI Engineer with a builder’s mindset to define and lead the technical direction of AI agents and intelligent workflows for IFS Nexus Black. You will operate at the intersection of product strategy, system architecture, and hands-on execution—turning ambiguous customer and business problems into scalable AI capabilities that move the company forward. This role requires deep production experience with LLM/agent systems, strong architectural judgment, and the ability to influence across teams. You will set the bar for how we design, evaluate, deploy, and scale AI systems safely and reliably.

Requirements

8–12+ years in software/AI engineering with a track record of building and scaling complex production systems.
Proven leadership in taking LLM/agent systems from concept to enterprise-scale deployment.
Experience influencing technical direction across teams or business units.
Deep expertise in: LLM architectures, agent frameworks, tool use, function calling
Retrieval-augmented generation (RAG), vector search, context assembly
Evaluation systems (offline/online testing, regression, quality metrics)
Observability and debugging for AI systems
Strong backend engineering fundamentals (distributed systems, services, queues, data modeling, CI/CD, cloud-native architecture).
Expert-level Python; strong familiarity with TypeScript or other backend languages.
Strong understanding of tradeoffs between experimentation speed and production reliability.
Exceptional product sense and business alignment.
Ability to navigate ambiguity and create clarity at both system and strategy levels.
Strong executive communication skills.
Demonstrated mentorship of senior engineers.
Track record of high-leverage technical decisions with measurable business impact.

Responsibilities

Technical Strategy & Architecture Leadership
Define the long-term architecture for AI agents, orchestration systems, retrieval pipelines, evaluation frameworks, and safety guardrails.
Establish technical standards and best practices for LLM usage, agent planning/execution, tool integration, observability, and governance.
Make high-leverage architectural decisions that balance innovation, reliability, cost, and security.
Drive build-vs-buy strategy across AI infrastructure (vector stores, orchestration layers, eval tooling, hosting, etc.).
0→1 Innovation to Scaled Systems
Lead rapid prototyping of AI agents and workflows; validate value with customers.
Architect and guide the transition from experimental POCs to resilient, scalable production systems.
Identify reusable primitives (agent frameworks, SDKs, evaluation harnesses) that accelerate future development.
Ensure systems are designed for maintainability, extensibility, and enterprise-grade reliability.
Cross-Functional & Cross-Org Influence
Partner with product leadership to shape AI strategy and roadmap.
Translate ambiguous business goals into technical investment areas and measurable outcomes.
Collaborate with data engineering, platform, and security teams to align infrastructure and governance.
Represent AI technical direction in executive discussions and customer engagements.
Evaluation, Safety & Quality at Scale
Design and institutionalize evaluation loops (offline benchmarks, regression suites, online experimentation, human review systems).
Establish quality metrics, golden sets, and safety guardrails across agent systems.
Lead efforts in observability, tracing, and failure analysis for AI workflows.
Ensure responsible AI practices and compliance requirements are embedded into system design.
Technical Leadership & Talent Development
Lead architectural reviews and raise the engineering quality bar.
Mentor senior engineers and shape engineering culture.
Drive alignment across teams building AI-enabled features.
Contribute to hiring and calibration for high-impact AI roles.