About this role
Engineers who thrive on end-to-end ownership, from raw data processing to production-grade agentic systems and enterprise architecture, will find a strong fit at Ivanti. The team builds autonomous endpoint management and IT solutions powered by the Ivanti Neurons platform, helping global organizations reduce complexity and secure technology smarter.
This practitioner will ingest structured and unstructured data, build predictive and prescriptive models, and ship token-efficient LLM agents. The role exists to establish foundational AI architectures, set technical standards, and deliver decision-grade analytics that drive concrete business actions across the company.
What you will do
- Unify structured data from Snowflake with messy unstructured sources like logs and transcripts to create clean modeling datasets.
- Deliver customer churn analytics featuring properly quantified uncertainty and confidence intervals rather than basic point estimates.
- Build forecasting, propensity, and optimization systems that move beyond predictions to drive concrete business actions.
- Design and deploy token-efficient LLM agents using careful context management, retrieval strategies, and model routing.
- Define enterprise reference architectures, integration patterns, and governance standards spanning data ingestion and MLOps.
- Establish evaluation frameworks, monitoring, and guardrails for drift, bias, safety, and cost across classical and generative AI.
- Translate ambiguous business problems into technical solutions and communicate tradeoffs clearly to non-technical stakeholders.
What you need
- Strong hands-on data engineering experience with Snowflake, SQL, and the handling of unstructured data sources.
- Solid applied statistics background for building churn and retention models while expressing uncertainty using confidence intervals.
- Demonstrated history of shipping predictive and prescriptive analytics that successfully influenced business decisions.
- Production experience building LLM and agentic systems using frameworks such as LangGraph, CrewAI, or custom orchestrators.
- Practical production experience with retrieval-augmented generation including chunking, hybrid search, and reranking.
- Ability to design, document, and defend end-to-end system architectures that other engineers can build upon.
- Strong proficiency in Python paired with a software engineering mindset covering testing, version control, and CI/CD pipelines.
- Excellent written and verbal communication skills suited for working asynchronously in a distributed team environment.
Nice to have
- Cloud certifications like AWS Solutions Architect, Google Cloud Professional ML Engineer, or Azure AI Engineer
- TOGAF certification for enterprise architecture
- Experience with inference optimization including quantization, model routing, caching, and serving frameworks
- MLOps and LLMOps tooling or platform-building experience
- Domain experience and prior work owning AI strategy or build-versus-buy decisions
Benefits
- Friendly flexible working model supporting work-life balance at home or in the office
- Competitive compensation and total rewards including health, wellness, and financial plans
- Collaboration across global, diverse teams spanning 23 plus countries
- Access to learning and development tools and programs
- Inclusion initiatives focused on equity, belonging, and diverse hiring
Skills and tech stack
Questions candidates ask
What is the work flexibility policy?
Ivanti offers a friendly flexible working model that supports work-life balance, allowing employees to empower excellence whether working from home or in the office.
What data sources and tools will I work with?
You will ingest structured data from Snowflake alongside unstructured sources like text, documents, logs, and transcripts, utilizing Python, SQL, and agent frameworks like LangGraph and CrewAI.
How can I request accommodations during the hiring process?
Applicants who need adjustments during the process can reach out to talent@ivanti.com for assistance.