Specialist II - Data Science

Summary:

• Location: Irvine, CA
• Work Mode: Hybrid schedule (2–3 days/week onsite at the company’s Irvine office, 1 day/week onsite at the downtown Los Angeles office, and 1 day/week remote)

Responsibilities:

• Build and operationalize LLM-powered applications using RAG, embeddings pipelines, prompt orchestration, and evaluation frameworks.
• Design and implement vector search solutions using Amazon OpenSearch.
• Develop graph-based knowledge systems using Amazon Neptune.
• Integrate supporting services including Amazon ElastiCache (Redis) and DynamoDB.
• Implement agentic workflows using LangGraph, AutoGen, CrewAI, or similar frameworks.
• Work with LangChain and LlamaIndex for retrieval orchestration and context management.
• Evaluate models and retrieval strategies based on latency, cost, accuracy, and scalability.
• Design and develop scalable data pipelines using Databricks and Apache Spark.
• Build ingestion, transformation, document processing, embedding generation, and indexing pipelines.
• Establish data quality standards including validation and monitoring.
• Implement governance practices including classification, access controls, lineage, and auditability.
• Develop secure and scalable backend services exposing AI capabilities.
• Define API standards, versioning, resiliency, and reusable platform services.
• Build and manage CI/CD pipelines for AI and data workloads.
• Deploy and manage applications using Docker and Kubernetes.
• Support blue/green deployments, canary releases, rollback strategies, and feature flags.
• Implement observability, monitoring, alerting, and cost optimization.
• Define and track quality metrics including grounding, retrieval relevance, consistency, latency, and cost.
• Implement prompt/version tracking and evaluation pipelines.
• Establish secure AI practices including access control, data protection, responsible AI, and compliance standards.

Requirements:

• Strong experience with Generative AI and LLM systems (RAG, embeddings, prompt engineering).
• Hands-on AWS experience.
• Expertise in OpenSearch, Neptune, DynamoDB, and ElastiCache (Redis).
• Experience with LangChain, LlamaIndex, LangGraph, AutoGen, or CrewAI.
• Strong Python programming skills.
• Experience with Databricks and Apache Spark.
• Solid understanding of data pipelines, distributed systems, and API development.
• Bachelor’s or Master’s degree in Computer Science, Data Science, AI, or related field.
• Proven experience building and scaling production-grade AI platforms.
• Strong experience delivering end-to-end AI/ML lifecycle solutions.

Preferred Skills:

• Experience with LLM observability and evaluation frameworks.
• Knowledge of AI governance and compliance practices.
• Experience with Kubernetes and advanced MLOps concepts.
• Familiarity with MCP patterns and agent-based architectures.