AI Engineer, Enterprise Data & Generative AI

Sagent Pharmaceuticals•Hoffman Estates, IL

About The Position

Sagent is seeking a highly motivated AI Engineer to design, build, and deploy enterprise-grade AI solutions that leverage our Enterprise Data Warehouse (EDW), ERP systems, and cross-functional business data to generate measurable business value. This role will focus on building Retrieval-Augmented Generation (RAG) systems, enterprise copilots, text-to-SQL interfaces, and advanced analytics solutions that enable Finance, Supply Chain, Manufacturing, and Commercial teams to make faster, data-driven decisions. The ideal candidate combines strong machine learning and generative AI expertise with cloud-native engineering skills and the ability to translate enterprise data into scalable AI applications.

Requirements

Master’s degree in Data Science, Information Management, Computer Science, Engineering, or related field.
1–3 years of hands-on experience building AI/ML or LLM-based systems.
Strong programming skills in Python and SQL.
Experience with transformer models and embedding frameworks.

Nice To Haves

Experience building Text-to-SQL systems.
Exposure to enterprise data warehouse environments.
Experience in regulated industries (pharmaceutical or healthcare preferred).
Familiarity with AI model evaluation metrics and governance frameworks.
Experience mentoring or reviewing AI project architecture.

Responsibilities

Design and implement Retrieval-Augmented Generation (RAG) pipelines over structured (EDW) and unstructured enterprise data.
Develop Text-to-SQL systems enabling natural language access to EDW datasets.
Build metadata-aware retrieval systems to improve grounding and reduce hallucination risk.
Optimize chunking, embedding strategies, and retrieval pipelines for production performance.
Establish LLM evaluation frameworks including grounding precision and hallucination tracking.
Partner with business stakeholders to develop AI solutions supporting:
Finance
Revenue and margin variance copilots
Cash flow and forecasting assistants
Contract and rebate intelligence tools
Supply Chain & Manufacturing
Demand forecasting enhancement
Inventory risk alerts and expiry analytics
Production variance insights
Commercial
Sales performance summarization
Portfolio performance copilots
Contract intelligence search assistants
Build production-grade LLM applications using modern frameworks (e.g., LangChain, LangGraph).
Integrate OpenAI, open-source, or cloud-native foundation models as appropriate.
Implement caching and inference optimization strategies to manage cost and latency.
Establish guardrails and prompt security controls to prevent data leakage.
Develop enterprise AI governance standards for model usage and evaluation.
Deploy AI workloads using AWS services such as S3, Glue, Athena, SageMaker, Bedrock, Lambda, and OpenSearch.
Containerize AI services using Docker and deploy via Kubernetes where required.
Build scalable APIs and services to integrate AI capabilities into business workflows.
Monitor model performance, usage metrics, and cloud cost optimization.
Build and maintain ETL/ELT pipelines feeding AI models from EDW, ERP, supply chain, and finance systems.
Design structured metadata schemas to improve retrieval precision.
Ensure compliance with enterprise data governance and security standards.
Implement model monitoring for drift, usage tracking, and performance validation.
Establish policies for responsible AI use in a regulated environment.
Partner with IT Security and Compliance teams to ensure safe AI deployment.
People and team leadership skills; must be able to work closely with functional areas and establish alignment across the organization