S

SailPoint

Identity governance and access security software

Senior Business Analyst - Context Layer, Semantic Layer

Business AnalysisConfirmed live in the last 24 hours
Full-timePune, Maharashtra, IndiaNo salary listedIn-person

About the Job

Requirements

  • At least 6 years of experience as a Business Analyst, Data Analyst, or Knowledge/Ontology Analyst, with recent exposure to AI/LLM-powered platforms, copilots, or agentic systems.
  • Strong grasp of semantic modeling concepts, including metrics layers, ontologies, and knowledge graphs, and how they differ when designed for machine/agent consumption versus human dashboards.
  • Understanding of how large language models consume structured context, including retrieval-augmented generation architectures, embeddings, chunking strategies, function/tool calling, and prompt/context engineering.
  • Experience translating ambiguous business language into precise, structured, disambiguated definitions.
  • Strong SQL skills and ability to work with data models, APIs, or knowledge graphs that agents query against.
  • Experience writing and structuring documentation, including glossaries, business rules, and metadata, in formats consumable by both people and AI systems.
  • Ability to extract and reconcile business logic from multiple domain experts.

Responsibilities

  • Define and maintain the semantic model—metrics, dimensions, entities, synonyms, and relationships—that AI agents use to map natural-language business questions to correct data queries, including SQL, semantic-layer APIs, or knowledge graph traversals.
  • Design metric and entity definitions for agent readability, including unambiguous naming, explicit synonyms/aliases, and disambiguation rules for overloaded business terms.
  • Partner with AI engineers to structure the semantic layer for tool-calling/function-calling patterns, ensuring agents select the right metric, filter, and grain when generating queries.
  • Continuously test and tune semantic definitions against agent query failures, misinterpretations, and hallucination patterns.
  • Design the context layer that supplies agents with business rules, caveats, definitions, data lineage, and usage guardrails to ground responses, for example through retrieval-augmented generation retrieval, system prompts, or structured metadata injection.
  • Curate and structure business context objects—glossaries, policy documents, calculation logic, exceptions, and edge cases—into retrieval-optimized formats using chunking strategies, embeddings-friendly structure, and metadata tagging.
  • Define context scoping and prioritization rules so agents retrieve relevant and correct context for each query while minimizing noise and conflicting information.
  • Work with platform teams to version and govern context content so agent behavior stays aligned as business rules evolve.
  • Partner with AI/ML engineers to evaluate agent outputs against expected business answers and identify root causes when agents misinterpret semantic or contextual inputs.
  • Build test question sets (golden queries) representing real business questions to validate semantic/context-layer coverage and accuracy.
  • Define feedback loops that trace incorrect agent responses to semantic gaps, missing context, or ambiguous definitions, and drive remediation.
  • Support prompt/context engineering by translating business nuance into structured inputs agents can reliably use.
  • Act as the primary bridge between business domain experts and the AI platform/engineering team, ensuring business intent is faithfully encoded into semantic and context structures.
  • Collaborate with business stakeholders, data engineers, and architects to ensure the underlying data model supports the semantic layer used by the agent.
  • Work with data governance teams to ensure context/semantic content meets accuracy, security, and access-control standards, including respecting row-level security in agent-generated queries.
  • Maintain a living business glossary and context repository as the authoritative source for human users and AI agents.
  • Document the semantic layer's coverage, known gaps, and disambiguation logic for auditability.
  • Establish a review/change-management process for updating semantic and context definitions as the business evolves without degrading agent performance.
  • Meet with business stakeholders, AI/ML engineering, data platform, and architecture teams to understand the current agent stack, including the LLM used, orchestration framework, RAG setup, and any semantic-layer tooling.
  • Meet with business stakeholders across key domains to understand how they define and use core metrics and entities.
  • Inventory existing semantic assets, including BI semantic layers, data dictionaries, business glossaries, and metric definitions, and assess their quality, coverage, and consistency.
  • Run or observe the AI agent against sample real business questions and log failures, hallucinations, or term misinterpretations.
  • Review existing data models, lineage documentation, and access/security controls relevant to agent queries.
  • Identify three to five high-value, high-ambiguity business domains to prioritize.
  • Produce a current-state assessment of semantic-layer maturity, context-layer gaps, and agent failure patterns; an initial glossary of ambiguous/overloaded terms; an initial inventory of context-layer and semantic-layer objects, tables, fields, domain terms, rules, processes, metrics, and formulae; a stakeholder map identifying metric/definition owners; 15–20 golden queries; and three pilot use cases for the context layer.
  • Define structured metric and entity specifications for priority domains, including name, definition, synonyms/aliases, calculation logic, grain, and owner.
  • Design disambiguation rules for known overloaded terms, including department-specific definitions of terms such as revenue.
  • Structure context objects for RAG retrieval and work with AI engineers on chunking, tagging, and metadata format.
  • Run the golden-query set against the agent before and after semantic/context updates and document accuracy shifts.
  • Set up a lightweight review/change-management process for updating definitions without breaking agent behavior.
  • Begin building the living business glossary/context repository as a shared source of truth.
  • Establish a feedback loop that tags agent failures by root cause (semantic gap, context gap, or data issue) and routes them to the appropriate fix owner.
  • Deliver semantic-layer version 1 for three to five priority domains, integrated into the agent's query/tool-calling logic; context-layer version 1 integrated into RAG or prompt context; an expanded 40–50-query golden test suite with pass/fail tracking; and an initial governance/change-management process document.
  • Expand semantic/context coverage to additional business domains beyond the initial priority set.
  • Formalize golden-query evaluation as an ongoing QA process, run weekly or bi-weekly, and track trends over time.
  • Present before/after agent-accuracy results to leadership and stakeholders with examples of resolved ambiguity/hallucination.
  • Finalize the governance model, including approval of new metric definitions, versioning, and updates or deprecation of context as business rules change.
  • Train business users and analysts to contribute to or query the glossary/context repository.
  • Document known limitations and a roadmap for the next 90 days.
  • Deliver a documented, governed semantic and context layer covering most high-value business domains; an ongoing QA/evaluation process with historical accuracy tracking; a stakeholder-facing impact summary covering accuracy improvement, reduced hallucinations, and adoption metrics; and a 90-day forward roadmap.

Desired Qualifications

  • Hands-on experience with semantic-layer tools such as UnifyApp, Atlan, dbt Semantic Layer, Cube, AtScale, or LookML, and AI orchestration frameworks such as LangChain, LlamaIndex, Semantic Kernel, or similar.
  • Experience with vector databases and RAG pipeline design, such as Pinecone, Weaviate, or pgvector.
  • Familiarity with knowledge graph technologies such as Neo4j and RDF/OWL for entity/relationship modeling.
  • Experience evaluating LLM/agent outputs, including building evaluation harnesses, golden datasets, or human-in-the-loop review processes.
  • Background in AI governance, model risk, or responsible AI practices applied to enterprise data.
  • Exposure to enterprise data catalogs such as Collibra, Alation, Atlan, or Purview and metadata management.

About the Company

SailPoint

Identity governance and access security software

SailPoint provides identity security solutions that help enterprises manage digital identities. Its products—IdentityIQ, IdentityNow, and File Access Manager—offer identity governance, access management, and file access control with automated workflows, policy enforcement, and analytics, using AI and ML to improve decisions and detect anomalies. The company differentiates itself with comprehensive governance across on-prem, cloud, and hybrid environments and a subscription-based model that combines software licenses, maintenance, and professional services. Its goal is to help customers meet regulatory requirements, reduce risk, and maintain strong security across large organizations, governments, and financial institutions.

Company size
1,001-5,000
Company stage
IPO
Headquarters
Austin, TX
Founded
2004

Recently Posted Jobs

Explore more opportunities at SailPoint

See more jobs