What are the responsibilities and job description for the Artificial Intelligence Specialist position at System Soft Technologies?
Job Summary
We are hiring an AI Lead to serve as the technical authority and strategic driver for how artificial intelligence is designed, implemented, and evolved within Advisory’s enterprise delivery platform. This role is responsible for maintaining a deep, hands-on understanding of modern AI systems, monitoring market and research trends, and translating those advancements into practical, enterprise-ready platform capabilities. The AI Lead defines how models are used, intelligence is orchestrated, context is assembled, agents behave, and AI quality and trust are measured at scale.
Responsibilities
AI Strategy & Market Intelligence
Continuously track and evaluate:
o LLM and foundation model advancements
o Agent frameworks and orchestration patterns
o Retrieval, memory, and context management techniques
o AI evaluation, safety, and governance approaches
Translate emerging AI trends into:
o Platform design principles
o Proofs of concept and experiments
o 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:
o Model selection and benchmarking
o Versioning and lifecycle management
o Cost, performance, and latency trade-offs
o Fallback and redundancy strategies
• Establish best practices for:
o Prompt and instruction design
o Skill and Tool calling
o Structured outputs and determinism
Semantic Routing & Orchestration
Design and evolve the platform’s semantic routing layer, including:
o Intent detection and task classification
o Routing to appropriate models, agents, or workflows
o Context-aware decisioning based on workspace state
• Define orchestration patterns for:
o Multi-step and parallel execution
o Long-running and asynchronous tasks
o Human-in-the-loop controls
• Ensure routing logic is transparent, testable, and tunable.
Agent Architecture & Execution
Consult on the firm’s agent strategy, including:
o When to use agents vs. workflows vs. direct LLM calls
o Agent composition, memory, and tool access
o Guardrails and behavioral constraints
• Partner with engineering to implement:
o Agent frameworks and runtime infrastructure
o Monitoring and debugging capabilities
Ensure agents are:
o Predictable and auditable
o Aligned to service methods and delivery workflows
o Safe for enterprise and client-facing use
Workspace Context & RAG Architecture
• Own the design of contextual intelligence within workspaces, including:
o Document ingestion, chunking, and enrichment strategies
o Vector, keyword, and hybrid retrieval approaches
o Context assembly across client data, firm IP, and engagement artifacts
Define standards for:
o Source attribution and transparency
o Data isolation and compliance
o 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:
o Task-based and scenario-driven evaluations
o Regression testing for prompts, agents, and routing logic
o Comparative benchmarking across models and configurations
Define metrics for:
o Accuracy, relevance, and consistency
o Cost efficiency and latency
o User trust and explainability
• Partner with engineering and risk teams to ensure:
o Observability into AI behavior
o Safe deployment and controlled experimentation
o Continuous improvement loops based on real usage
Platform Enablement & Collaboration
Work closely with:
o Platform engineering teams
o Product and design partners
o Consulting and delivery leaders
• Provide technical guidance on:
o How AI capabilities should be embedded into platform features
o Where AI adds leverage vs. complexity
Support enablement through:
o Technical documentation and reference architectures
o Internal education and design reviews
o Advisory support for high-impact use cases
Governance & Responsible AI
• Define technical guardrails that support:
o Security, privacy, and data residency
o Responsible AI principles
o Regulatory and client requirements
Ensure AI systems are:
o Explainable where required
o Observable and auditable
o Designed for controlled evolution over time