AI Lead – Platform Intelligence & Applied AI

AI Lead – Platform Intelligence & Applied AI

Chicago, IL (Remote)

Duration: 6-12 Months

AI Strategy & Market Intelligence

• Continuously track and evaluate:
• LLM and foundation model advancements
• Agent frameworks and orchestration patterns
• Retrieval, memory, and context management techniques
• AI evaluation, safety, and governance approaches
• Translate emerging AI trends into:
• Platform design principles
• Proofs of concept and experiments
• Scalable, production-ready capabilities
• Advise leadership on when and how new AI capabilities should be adopted.

Model & Intelligence Management

• Own the strategy for LLM and model usage across the platform, including:
• Model selection and benchmarking
• Versioning and lifecycle management
• Cost, performance, and latency trade-offs
• Fallback and redundancy strategies
• Establish best practices for:
• Prompt and instruction design
• Skill and Tool calling
• Structured outputs and determinism

Semantic Routing & Orchestration

• Design and evolve the platform's semantic routing layer, including:
• Intent detection and task classification
• Routing to appropriate models, agents, or workflows
• Context-aware decisioning based on workspace state
• Define orchestration patterns for:
• Multi-step and parallel execution
• Long-running and asynchronous tasks
• Human-in-the-loop controls
• Ensure routing logic is transparent, testable, and tunable.

Agent Architecture & Execution

• Consult on the firm's agent strategy, including:
• When to use agents vs. workflows vs. direct LLM calls
• Agent composition, memory, and tool access
• Guardrails and behavioral constraints
• Partner with engineering to implement:
• Agent frameworks and runtime infrastructure
• Monitoring and debugging capabilities
• Ensure agents are:
• Predictable and auditable
• Aligned to service methods and delivery workflows
• Safe for enterprise and client-facing use

Workspace Context & RAG Architecture

• Own the design of contextual intelligence within work spaces, including:
• Document ingestion, chunking, and enrichment strategies
• Vector, keyword, and hybrid retrieval approaches
• Context assembly across client data, firm IP, and engagement artifacts
• Define standards for:
• Source attribution and transparency
• Data isolation and compliance
• Relevance, freshness, and performance
• Continuously evaluate new approaches to memory, retrieval, and grounding.

AI Evaluation, Testing & Trust

• Establish the platform's AI evaluation and testing framework, including:
• Task-based and scenario-driven evaluations
• Regression testing for prompts, agents, and routing logic
• Comparative benchmarking across models and configurations
• Define metrics for:
• Accuracy, relevance, and consistency
• Cost efficiency and latency
• User trust and explainability
• Partner with engineering and risk teams to ensure:
• Observability into AI behavior
• Safe deployment and controlled experimentation
• Continuous improvement loops based on real usage

Platform Enablement & Collaboration

• Work closely with:
• Platform engineering teams
• Product and design partners
• Consulting and delivery leaders
• Provide technical guidance on:
• How AI capabilities should be embedded into platform features
• Where AI adds leverage vs. complexity
• Support enablement through:
• Technical documentation and reference architectures
• Internal education and design reviews
• Advisory support for high-impact use cases

Governance & Responsible AI

• Define technical guardrails that support:
• Security, privacy, and data residency
• Responsible AI principles
• Regulatory and client requirements
• Ensure AI systems are:
• Explainable where required
• Observable and auditable
• Designed for controlled evolution over time

• Strong experience with AI strategy, platform intelligence, and applied AI solutions.
• Hands-on experience with LLMs, foundation models, and model lifecycle management.
• Experience designing and implementing agent architectures and orchestration frameworks.
• Strong understanding of RAG architecture, retrieval strategies, embeddings, vector databases, and context management.
• Experience with prompt engineering, structured outputs, tool calling, and AI workflow design.
• Experience designing semantic routing, intent classification, and AI decisioning systems.
• Strong knowledge of AI evaluation frameworks, benchmarking methodologies, testing strategies, and observability.
• Experience implementing AI governance, security, privacy, and responsible AI practices.
• Ability to translate emerging AI technologies into enterprise-scale platform capabilities.
• Strong collaboration skills across engineering, product, design, consulting, and leadership teams.