What are the responsibilities and job description for the Gen AI & Data Engineer position at Icon International Group LLC?
Lead Gen AI & Data Engineer
Charlotte, NC – 3 days/week onsite role
Design and develop Agentic AI systems using Google ADK, LangChain, and LangGraph, including multi-agent orchestration, state management, and tool integration leveraging enterprise approved LLMs.
Integrate agents with enterprise Systems of Record (SoRs) by building reliable data pipelines, APIs, and connectors across structured and unstructured sources.
Integrate organization-approved foundation models (like Anthropic, Google Gemini etc.) into Agentic task-based workflows.
Partner with Process Excellence and Ops teams to ideate and implement AI copilots and AI Agents for business functions.
Develop scalable Python-based services for agent workflows, incorporating RAG, tool calling, memory, and structured outputs.
Engineer data ingestion and transformation pipelines (batch/streaming) to enable high-quality, governed data access for AI agents.
Write and optimize complex SQL queries for analytics, feature extraction, and real-time agent decisioning.
Implement observability, evaluation, and guardrails across both data and AI layers, ensuring performance, quality, compliance, and cost efficiency.
Use SQL, Python, and cloud-native tools (Google Cloud Platform, Azure, or AWS) to ensure data quality and lineage.
Mandatory Skills
5 years in Gen AI, AI Data Engineering, and Agentic AI-focused roles.
Advanced Prompt Engineering, Context Engineering skills, Python skills.
Hands-on experience building agentic AI solutions using Google ADK LangChain/LangGraph, including orchestration and tool usage patterns.
Strong Python development skills for backend services, workflow engines, and AI pipelines.
Solid data engineering expertise:
- Building ETL/ELT pipelines
- Integrating data from multiple SoRs (APIs, DBs, files, streams)
- Working with data quality, schema evolution, and lineage
- Advanced SQL proficiency(complex joins, window functions, query optimization).
- Experience with RAG architectures and integrating LLMs with enterprise data sources (vector stores relational systems).
- Production-grade engineering practices: testing, CI/CD, logging, monitoring, and error handling.‘
- Prompt engineering / Prompt finetuning
Desired Skills
Experience with modern data stack tools(e.g., dbt, Airflow/Composer, Kafka/PubSub, BigQuery/Snowflake).
Familiarity with vector databases and hybrid retrieval strategies.
Experience deploying solutions on Google Cloud Platform (preferred)or other cloud platforms with scalable architectures.
Knowledge of data governance, security, and PII handling in AI/data pipelines.
Exposure to LLM Ops frameworks(evaluation, prompt/version management, tracing, cost optimization).
Experience implementing guardrails and safety controls for enterprise AI agents.