Senior Engineer – Semantic & Agentic Intelligence
$115,000 per year
Apply (opens in a new tab)Senior Engineer – Semantic & Agentic Intelligence
Posted 2 days ago
SENIORITY
Lead
SALARY
$115,000 per year
About the role
- 6+ years of relevant experience in Data Engineering, Semantic Modeling, or AI/ML Engineering, with senior or lead experience
- College degree in Computer Science, Mathematics, Business Administration, or a related field
- Experience with a supported business area is preferred (e.g., Provider Network, Claims, Membership, Digital Solutions, Pricing)
- Equivalent combination of education and experience
- Dimensional Modeling & Data Platform
- Deep expertise in dimensional modeling with strong command of grain, bridge tables, many-to-many relationships, and slowly changing dimensions (SCDs)
- Awareness of common data modeling pitfalls and how to prevent them
- Strong SQL skills on Snowflake or a comparable cloud data warehouse
- Experience with dbt, ELT/ETL design patterns, and orchestration tools (Airflow or similar)
- Understanding of data governance, security, compliance, and enterprise platform ownership
- Semantic Layer & Governed Metrics
- Experience defining governed metrics in a semantic or metrics layer
- Has built and deployed a semantic layer (SSAS, LookML, dbt Semantic Layer, or similar) used directly by business users
- Experience evaluating AI-generated answers and diagnosing and fixing root causes in the semantic layer
- Agentic AI & LLM Engineering
- Experience deploying and monitoring AI agents in a governed, regulated environment
- Built LLM/agentic applications including RAG pipelines, embeddings/vector search, prompt engineering, tool/function calling, and agent orchestration frameworks
- Experienced with Snowflake Cortex (Analyst, Search, Agents) or comparable native AI tooling
- Experience developing and managing AI agents for use cases such as:
- Prior authorization
- Member support
- Care gap identification
- Utilization analytics
- Anomaly/outlier detectionAI Ops & Observability
- Implemented evaluation frameworks, guardrails, and observability for AI agents covering accuracy, hallucination detection, latency, and cost
- Familiarity with scoring techniques such as F1 scoring and related evaluation metrics
- Experience with model/agent monitoring, cost optimization, and performance tuning
- Healthcare Domain Knowledge
- Working knowledge of payer data: claims (837/835), eligibility, enrollment, and provider data
- Familiarity with healthcare standards: HL7/FHIR, ICD-10, CPT/HCPCS
- Experience with ontologies, knowledge graphs, or formal business vocabularies
- Built and managed MLOps pipelines with familiarity with ML models including regression and ensemble methods (e.g., KNN, XGBoost, Random Forest, Decision Trees)
- Experience building consumer-facing AI applications or features involving inference
- Experience building multi-tier AI applications or multi-agent workflows, including multimodal LLM experience
- Experience with statistical and predictive modeling (regression, classification, clustering, time series forecasting)
- Experience with BI and visualization tools (Tableau, Power BI, Looker) and translating analytical findings into business narratives
- Exposure to experimentation and hypothesis testing (A/B testing, statistical significance)
- What You Will Do at Cambia:
- Lead and mentor Data and AI Engineers and drive engineering standards and best practices across the squad
- Design, build, and own scalable dimensional models, semantic layers, and governed metric definitions used by business users and AI systems
- Develop and deploy AI agents for healthcare use cases (prior authorization, member support, care gaps, utilization analytics, anomaly detection) in a governed, regulated environment
- Build LLM/agentic applications including RAG pipelines, vector search, prompt engineering, and agent orchestration leveraging Snowflake Cortex or comparable tooling
- Implement AI Ops practices including evaluation frameworks, guardrails, observability, and cost/performance optimization for deployed agents
- Optimize platform performance including query tuning, compute sizing, workload isolation, and cost management
- Partner with Analytics, Product, Governance, QA, and Business teams to deliver high-quality, observable, and trustworthy data and AI solutions
- Contribute to platform strategy, risk assessments, and adoption of modern practices (DataOps, CI/CD, AI tooling)
- Ensure data quality, testing, documentation, and knowledge sharing across the team
- Demonstrate technical leadership by breaking down complex work and delivering measurable value in squad/model environments
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.
