Principal AI Knowledge AI Architect
Principal AI Knowledge AI Architect
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Not Disclosed
Salary Not Disclosed
1 Vacancy
Job Description
We are seeking a Principal AI Knowledge AI Architect to design and lead the architecture for next-generation knowledge and RAG systems that enable reasoning-driven AI assistants to deliver precise contextually relevant answers at scale. This role focuses on advanced RAG pipelines leveraging ontologies dynamic content ingestion agentic retrieval data synchronization with enterprise platforms and continuous knowledge health monitoring to ensure high-fidelity trustworthy knowledge delivery.
You will architect the knowledge layer of our AI Agentic Platform integrating enterprise content repositories knowledge bases APIs and external tools into an agent-driven reasoning and retrieval engine.
Key Responsibilities:
Advanced RAG Architecture
- Architect and implement multi-layer RAG pipelines leveraging ontologies semantic graphs embeddings and hybrid retrieval strategies.
- Design agentic RAG workflows where autonomous agents reason about query decomposition multi-hop retrieval and context stitching for better factual accuracy.
- Build hierarchical and ontology-based knowledge graphs to improve entity resolution semantic search and contextual reasoning.
- Optimize retrieval for domain-specific knowledge using structured unstructured data fusion.
Knowledge Ingestion & Synchronization
- Lead development of content ingestion pipelines for enterprise sources (Confluence SharePoint Google Drive Salesforce KB ServiceNow KB etc.)
- Design real-time data sync connectors and ETL frameworks to keep knowledge sources fresh and in sync with external systems.
- Implement document parsing enrichment chunking metadata tagging and semantic indexing pipelines at scale.
Agentic Knowledge & Reasoning Integration
- Architect agentic knowledge workflows where agents autonomously evaluate retrieve and cross-reference multi-source knowledge.
- Enable agents to invoke external APIs/tools dynamically to complement RAG with transactional or dynamic information retrieval.
- Integrate multi-modal RAG (text images tables PDFs) into reasoning loops for richer AI responses.
Knowledge Quality & Health Monitoring
- Develop knowledge health check pipelines to automatically validate knowledge freshness detect stale or redundant articles and recommend updates.
- Implement automated knowledge evaluation using LLMs (hallucination detection coverage analysis answer accuracy).
- Define governance policies for knowledge versioning lifecycle management and auditing.
Scalability Security & Compliance
- Architect multi-tenant enterprise-ready knowledge systems with strict access controls encryption and compliance (SOC2 HIPPA GDPR).
- Ensure cost-efficient vector database and embedding management strategies (e.g. partitioning caching tiered storage).
Thought Leadership & Collaboration
- Mentor engineers on best practices for RAG pipelines knowledge representation and semantic search.
- Work with product leadership to define long-term knowledge strategy for powering enterprise-grade agentic AI assistants.
- Collaborate closely with LLM engineers on optimizing retrieval-planning-generation loops for factual accuracy and latency.
Please note: This is a hybrid role that will be based in San Mateo CA or Bellevue WA and requires an in-office presence three days per week (Tuesday - Thursday).
Qualifications :
Required Qualifications
- 10 years in software architecture with at least 3 years in AI-driven knowledge systems RAG pipelines or semantic search
- Deep expertise in retrieval techniques (vector search hybrid search ontology-based retrieval) and knowledge graph design
- Experience with ontology design and reasoning (OWL SPARQL etc.) for enterprise knowledge modeling
- Proven experience building RAG pipelines with LLMs (OpenAI Anthropic LLaMA etc.) integrated into production systems
- Strong proficiency in Java & Python and AI/ML frameworks (LangChain LangGraph etc.)
- Knowledge of vector DBs (Pinecone ElasticSearch etc.) and graph DBs (Neo4j etc.)
- Experience building enterprise knowledge ingestion frameworks from CMS/CRM/ITSM platforms (e.g Salesforce ServiceNow)
- Background in document parsing (OCR PDFs HTML) metadata enrichment and semantic embeddings
- Expertise in scalable cloud-native architecture (Kubernetes event-driven microservices streaming pipelines)
- Understanding of agentic AI frameworks (LangChain LangGraph) and their integration with retrieval for reasoning
Preferred Qualifications:
- Familiarity with self-healing knowledge pipelines (auto-detection and repair of broken links stale knowledge)
- Strong grounding in AI safety and governance for enterprise knowledge systems
- Contributes to open-source RAG or knowledge graph frameworks are a plus
- Familiarity with multi-modal knowledge retrieval (image/document embeddings and cross-modal search)
Additional Information :
The annual base salary range for this position is $260500 - $374440.
Compensation is based on a variety of factors including but not limited to location experience job-related skills and level. Bonus/equity may be available.
Freshworks offers multiple options for dental medical vision disability and life insurances. Equity ESPP flexible PTO flexible spending commuter benefits and wellness benefits are also offered. Freshworks also offers adoption and parental leave benefits.
At Freshworks we are creating a global workplace that enables everyone to find their true potential purpose and passion irrespective of their background gender race sexual orientation religion and ethnicity. We are committed to providing equal opportunity for all and believe that diversity in the workplace creates a more vibrant richer work environment that advances the goals of our employees communities and the business.
Remote Work :
No
Employment Type :
Full-time
Employment Type
Full-time
