Data Scientist / AI Architect (Agentic AI & LLM Focus)

Job Title: Data Scientist / AI Architect (Agentic AI & LLM Focus)

Duration: 6-12+ Months Contract

Location: Irvine, CA - Onsite

Context & Objective

We are engaging a hands-on Data Scientist / AI Architect to design and deliver agent-based, AI-enabled workflows integrated with enterprise systems. The role requires close collaboration with internal teams and business stakeholders to translate use cases into scalable, production-grade solutions.

Core Responsibilities

Data Science & Agent-Oriented System Design

• Design, develop, and deploy Python-based data science solutions supporting:
• Agent-driven workflows (supervisor/sub-agent architectures, intelligent decision systems)
• Data pipelines, APIs, and enterprise system integrations for model deployment
• Multi-step, asynchronous processing and experimentation workflows
• Apply strong data science and engineering practices, including:
• Model validation and evaluation
• Testing and reproducibility
• Code quality, performance optimization, and error handling

AI / LLM-Enabled Solution Development

• Design and implement end-to-end LLM-powered solutions, including:
• Prompt engineering and context management to optimize model performance
• Structured output generation, validation, and post-processing for reliable outcomes
• Integrate LLMs into analytical pipelines and decision-making workflows

Stakeholder Collaboration

• Work closely with business stakeholders to:
• Translate business use cases into technical designs and acceptance criteria
• Communicate trade-offs across quality, cost, risk, and delivery timelines

Good to Have

Data Engineering for Retrieval-Based Systems

• Design and manage retrieval pipelines to support grounding and context enrichment, including:
• Vector databases and similarity search
• Search and indexing systems
• Storage solutions for source data and embeddings
• Caching strategies for performance and scalability

Cloud-Native Delivery (AWS Preferred)

• Deploy and manage AI/ML solutions on cloud platforms, with focus on:
• IAM and security best practices
• Scalability, resilience, and availability
• CI/CD pipelines and environment management

Integration & UX Enablement

• Integrate AI solutions with enterprise tools via secure APIs and gateways

• Collaborate with front-end teams (e.g., React) to enable seamless user experiences

Observability & Operations

• Implement monitoring across workflows, including:
• Logging, metrics, and tracing for agent pipelines and model calls
• Support performance tuning, incident diagnosis, and continuous optimization

Interview Focus Areas

• Hands-on experience in AI/LLM solution design and implementation
• Strong understanding of AI/ML/LLM libraries used in projects
• Experience with LLM fine-tuning (critical requirement)
• Experience in RAG (Retrieval-Augmented Generation) architectures