Lead AI Software Engineer (Remote)

Inspira Financial•Oak Brook, IL

1d•Remote

About The Position

The Lead AI Software Engineer is a hands-on builder responsible for the enterprise AI engineering foundation, including the semantic router, model and harness hosting, enterprise AI gateway, and AI operations layer used across the business. The role builds to architecture and standards established by CoE technical leadership and contributes design input to help shape them. It reports to the Sr. Director, AI Center of Excellence, in the Technology Department and has no direct reports. The role builds and operates shared AI platform capabilities and semantic routing; partners with AI-Ops on monitoring, evaluation, and governance guardrails; and develops secure, compliant AI integration patterns for a regulated financial services environment. It also scales agentic pipelines and multi-agent orchestration, delivers production AI services for CoE-enabled business functions, creates reusable components aligned to CoE reference architectures, evaluates AI workload economics, prototypes emerging capabilities, and mentors engineers across the CoE and partner teams. The position partners with security, risk, compliance, and data governance teams.

Requirements

Bachelor of Science in Computer Science.
At least 7 years building and operating production software, including at least 2 years delivering production AI, LLM, or ML systems, with a track record of building and shipping components of an enterprise-scale platform.
Experience building and operating production agentic workflows as state machines, including branching logic, retry and recovery paths, and precise control over multi-step process flow.
Knowledge of multi-agent system design, including role assignment and coordination, agent-to-agent conversation patterns, and code execution loops for iterative problem solving.
Deep fluency with AI-assisted development environments such as GitHub Copilot, Claude Code, or ONA, and experience helping teams adopt them and measure their impact.
Experience with semantic routing and model orchestration, including embedding-based intent analysis, deterministic fallback logic, and policy-based model selection across providers using cost, latency, and privacy criteria.
API and integration experience across REST, event-driven, and MCP patterns, including integrating AI into systems of record and workflow platforms.
Experience with observability and AI Ops for non-deterministic systems, including distributed tracing, behavioral analysis, usage and quality metrics, drift detection, and cost and latency telemetry for executive reporting.
Security-aware engineering experience handling PII and sensitive data, including encryption, secrets management, least-privilege access, and audit trails in a regulated environment.
Model hosting and serving experience, including deploying self-hosted or open-weight models, inference optimization, and gateway or proxy patterns in front of multiple models.
Experience in evaluation and reliability engineering for probabilistic systems, including evaluation harnesses, golden datasets, offline and online scoring, guardrails, red-teaming, hallucination mitigation, and human-in-the-loop review design.
Data engineering foundations for AI, including document ingestion and extraction pipelines, data source integration and mapping, embeddings, and data quality controls.
Technical leadership without formal authority, including contributing to architecture decision records and design reviews, mentoring early-career and senior engineers, and communicating trade-offs clearly.
Ability to deliver roadmap capabilities from discovery through prototype, production validation, and scale against defined business metrics.
Ability to move between abstract system thinking and tactical, incremental delivery while identifying a critical path and managing stakeholders.

Nice To Haves

Financial services, healthcare benefits, or other regulated-industry experience; HSA/FSA, claims, custody, or payments domain exposure is especially valuable.
Knowledge of AI governance and compliance frameworks such as NIST AI RMF, ISO/IEC 42001, model risk management, SOC 2, or HIPAA control environments.
Experience with rapid prototyping and feasibility assessment in an R&D or innovation capacity.
Experience facilitating technical learning sessions or pairing with engineers at varying skill levels.
Document intelligence and intelligent document processing experience, including OCR, extraction, and classification pipelines with measured accuracy targets.
Experience with decisioning and adjudication systems where machine decisions are reviewed, audited, and held to accuracy and turnaround standards.
Conversational and voice AI experience, including chat deflection, speech-to-text, call transcription and summarization, and authenticated, account-specific responses.
Experience with fraud, anomaly, and identity signal detection, including behavioral baselines, relationship or graph analytics, and detection of doctored or AI-generated media.
Experience with workflow and low-code automation platforms.

Responsibilities

Build and operate the enterprise shared AI platform, including semantic data, model, harness, and hosting capabilities for developer and in-product personalization use cases.
Build intelligent request routing using semantic analysis and deterministic logic to direct requests to suitable LLMs, internal tools, or agentic pools based on cost, latency, and privacy.
Partner with AI-Ops on metric-based reporting, quality, performance, and drift monitoring; build model evaluation harnesses; and support governance guardrails for safe AI use at scale.
Build secure and compliant AI integration patterns suitable for a regulated financial services environment.
Build and scale agentic pipelines and multi-agent orchestration across the software development lifecycle, from pilot programs to measured engineering capacity across product teams.
Deliver production AI services for document intelligence and claims adjudication, conversational and voice self-service, call intelligence, fraud and anomaly detection, and regulatory monitoring.
Build reusable components and standard patterns aligned with CoE reference architectures so other teams and embedded consultants can build AI solutions without rebuilding the foundation.
Evaluate AI workload unit economics, including cost per transaction, token and inference spend, latency budgets, and analyses supporting build-versus-buy and self-host-versus-vendor decisions.
Identify and prototype emerging AI capabilities relevant to the business and technology roadmap, using a building-block approach for scaling.
Build focused feasibility spikes and foundational components that can scale across teams, with clean handoffs.
Lead applied continuous-learning sessions and pair with engineering teams on new development methods and adoption of prototypes or patterns.
Coach embedded AI consultants and the coaching network on CoE patterns and standards to scale AI delivery capacity beyond the CoE.
Mentor Software Engineer I, II, and Senior-level engineers across the CoE and partner teams; participate in AI design reviews; and help resolve complex agentic and integration problems alongside Principal-level engineers.
Partner with security, risk, compliance, and data governance teams to support safe and compliant AI delivery.