Assent is seeking a Senior Data Engineer, AI/ML with deep expertise in knowledge base construction, retrieval-augmented reasoning (RAQ/RAG), and Generative AI data pipelines to help enable Assent’s R&D toward Agentic AI systems. You will design and maintain intelligent data infrastructures that supply context, memory, and reasoning capabilities to autonomous AI agents by connecting structured and unstructured enterprise data into continuously updated knowledge graphs and vectorized stores.
What You'll Do
- Design, build, and optimize data pipelines for Agentic and Generative AI systems, enabling context retrieval, multi-step reasoning, and adaptive knowledge updates.
- Develop and manage knowledge bases, vector stores, and graph databases to organize and retrieve information across diverse regulatory, product, and supplier domains.
- Engineer retrieval-augmented reasoning (RAQ/RAG) pipelines, integrating embedding generation, contextual chunking, and retrieval orchestration for LLM-driven agents.
- Collaborate cross-functionally with AI/ML, MLOps, Data, and Product teams to define data ingestion, transformation, and retrieval strategies aligned with evolving AI agent capabilities.
- Implement and automate workflows for ingestion of structured and unstructured content (documents, emails, APIs, metadata) into searchable, continuously enriched data stores.
- Design feedback and reinforcement loops that allow AI agents to validate, correct, and refine their knowledge sources over time.
- Ensure data quality, consistency, and traceability through schema validation, metadata tagging, and lineage tracking within knowledge and vector systems.
- Integrate monitoring and observability to measure retrieval performance, coverage, and model-data alignment for deployed agents.
- Collaborate with data governance and security teams to enforce compliance, access control, and Responsible AI data handling standards.
- Document schemas, pipelines, and data models to ensure reproducibility, knowledge sharing, and long-term maintainability.
- Stay at the forefront of AI data innovation, evaluating new technologies in graph reasoning, embedding architectures, autonomous data agents, and memory frameworks.
- Be familiar with corporate security policies and follow the guidance set out by processes and procedures of Assent.
What We're Looking For
- Deep expertise in knowledge base construction
- Deep expertise in retrieval-augmented reasoning (RAQ/RAG)
- Deep expertise in Generative AI data pipelines
- Proven ability to design, build, and maintain intelligent data infrastructures for AI agents
- Experience connecting structured and unstructured enterprise data into continuously updated knowledge graphs and vectorized stores
- Ability to enable dynamic retrieval, planning, and decision-making through data systems
- Experience collaborating with AI/ML engineers, data scientists, and product teams
- Ability to create scalable, auditable, and high-fidelity data pipelines for assistive and autonomous AI functions
- Familiarity with corporate security policies and adherence to Assent's processes and procedures
Technical Stack
- knowledge graphs
- vector stores
- graph databases
- embedding generation
- contextual chunking
- retrieval orchestration
- LLM-driven agents
- data pipelines
- schema validation
- metadata tagging
- lineage tracking
- monitoring and observability tools
- MLOps
- data ingestion systems
- data transformation frameworks
Team & Environment
- Cross-functional collaboration with AI/ML, MLOps, Data, Product, data governance, and security teams
