Data Scientist (Dataiku) - 180

DSM-H Consulting; Morton (IL); On-site; USD 110,000 - 170,000; Full time

Job summary

DSM-H Consulting is seeking an experienced specialist to build AI Agents using Dataiku and Snowflake, integrating workflows and automation across enterprise data sources.

You will implement multi-agent architectures, optimize prompts, and ensure testing, observability, and governance for production deployments.

Qualifications

• Years of experience: 5-7 years.
• Bachelor's degree in AI, Data Science or Computer Science.
• Internships accepted as work experience.
• No equivalent past titles provide the same background.

Responsibilities

• Understand objectives and design AI Agent solutions.
• Write Snowflake & Dataiku code to build AI Agents.
• Test outputs, iterate on code and improve reliability.

Skills

Multi-agent architecture

Agent collaboration

Prompt engineering

Dataiku app development

Security & governance

Enterprise integrations

Observability & testing

Deployment & operations

Cost optimization

Agent-to-Agent coordination

Education

Bachelor's in AI/DS/CS

Tools

Dataiku

Snowflake Cortex

LangGraph

Langchain

CrewAI

Job description

- As AI continues to evolve, there is a need to quickly learn new technology and build AI Agents and use them to create alerts & automate workflows. Most of the company's structured data resides in Snowflake. We are looking for an expert who has experience building AI Agents in Dataiku & Snowflake and using Dataiku recipes & Python for workflow automation

Typical task breakdown:

• Understand the objective
• Write code in Snowflake & Dataiku to build AI Agents
• Test output and update code

Interaction with team:

• Daily standup meetings

Team Structure

• Work on a project with 3 other people (includes project leader)

Work environment:

• Office

Education & Experience Required:

• Years of experience: 5-7years
• Degree requirement: Bachelors in AI, Data Science, Computer Science
• Do you accept internships as job experience: Yes
• Are there past or additional job titles or roles that would provide comparable background to this role: No

Top 3 Skills

• Built agents in Dataiku & Snowflake Cortex (critical) - structured data
• Workflow automation in Dataiku recipes & Python (write programming logic)
• Experience with LangGraph, Langchain, CrewAI

Additional Technical Skills

(Required)

• Multi-agent architecture and orchestration patterns
  • Agent collaboration, planning, delegation, and workflow orchestration
  • Reusable agent frameworks and reference architectures
• Security, access control, and governance
  • Role-based access control (RBAC), personas, authorization models, and guardrails
  • Auditability, and compliance considerations
• Enterprise integrations and data access patterns
  • Integration with Microsoft Teams, SharePoint, email, PDFs, and enterprise data sources
  • Event-driven and batch processing architectures
  • API and workflow integration best practices
• Agent evaluation, testing, and observability
  • Offline and online evaluation methodologies
  • Groundedness, relevance, hallucination detection, and task-success measurement
  • Automated regression testing, monitoring, observability, and performance tracking
• Prompt engineering and agent design patterns
  • Prompt optimization techniques, reusable prompts, skills, tools, and agent design frameworks
  • Approval processes for high-impact business decisions
  • Escalation paths, feedback loops, and continuous improvement mechanisms
• Dataiku application development and user experience
  • Dataiku WebApps, user experience design, and production-ready front-end development
  • Best practices for enterprise adoption and usability
• Deployment, operationalization, and scalability
  • Deployment automation, monitoring, and governance
• Cost and performance optimization
  • LLM selection and deployment strategies
  • Latency, token consumption, and operational cost management
  • Performance tuning and optimization best practices
• MCP experience in multi-agent system to coordinate communication across agents (Agent to Agent)