Senior AI Product Manager (Context Engineering)
This is the employer's own posting, not a copy on a job board.
What we know
Is it still open?
Confirmed still open
Last checked 3d ago — checked against the employer's own applicant tracking system, which is the company answering directly.
We re-read the employer's own applicant tracking system and the posting was still there. That is the company answering directly.
How old is it?
Posted 7d ago
The date the source published, not the day we noticed it (2026-10-26). Last seen at its source 5h ago.
We have tracked this listing since 27 Oct 2026 (6 days). The employer's own board has carried it every time we have read it, most recently 5 hours ago.
Is it remote?
US - Remote
That is the location the employer filed this posting under. Quoted as written — we do not re-word the source's own location.
Who may apply?
United States
The description states no restriction of its own. This is the source's own tag.
Pay
$125.3k–154.1k/yr
Read out of the job description by us, not from a structured field. Shown in the posting's own currency and period; we never convert.
Skills named in the ad
Recognised terms only, from a fixed vocabulary — this is what CV matching compares against.
Carried by 1 source
-
Workday employer's own board first seen 6d ago · last seen 5h ago
The listing
About the Team/Role:
At WEX, context engineering is the discipline of turning collective company knowledge, operational reality, and business logic into trusted, timely, and permission-aware context for AI agents. As a Senior AI Product Manager (Context Engineering), you will own the enterprise context layer that powers WEX's global fleet of AI agents. In this hands-on builder role within our Data, AI, Risk & Product organization, you will bridge unstructured knowledge, governed semantic data, and agent execution workflows, partnering directly with global engineering, data, and business teams to ensure every AI action is grounded, authorized, and accurate.
How you’ll make an impact:
- Strategy & Portfolio: Partner with global product, engineering, and business leaders to prioritize high-value context initiatives, sequencing workflows based on business impact, agent demand, source readiness, and risk.
- Governed Semantic Layer & NL-to-SQL: Own the semantic object roadmap for core enterprise entities (e.g., accounts, claims, plans), defining certified measures, join graphs, and Row-Level Security (RLS) to replace raw schema reasoning and eliminate hallucinations.
- Retrieval & Grounding: Establish enterprise standards for federated ingestion, chunking, caching, metadata, and citation enforcement, consolidating legacy knowledge APIs into unified, multi-tenant interfaces.
- Workflow Context Packs: Design and deliver production-ready context packs for critical operational workflows and SOPs, partnering directly with agent teams to inspect retrieval traces, debug failures, and optimize context consumption.
- Quality & Benchmarks: Build and run rigorous evaluation harnesses, golden datasets, error taxonomies, and go/no-go quality gates to benchmark retrieval relevance, query precision, and agent containment.
- Governance & Value Realization: Embed auditability, data lineage, least-privilege access, and responsible AI guardrails into the context layer by design, tracking ROI through API cost reduction, task resolution lift, and operational risk mitigation.
Experience you’ll bring:
- Education: Bachelor's degree in Computer Science, Engineering, Business, or a related field, or equivalent practical experience.
- Experience: Senior-level Product Management experience owning data platforms, enterprise search/retrieval systems, semantic layers, API products, or internal developer platforms consumed by engineering teams.
- Technical Skills: Deep understanding of applied generative AI and agentic systems, including advanced RAG, embeddings, chunking, metadata management, grounding, and context window assembly.
- Data Modeling & SQL: Strong experience working with structured enterprise data, relational models, certified metrics, and the failure modes of natural-language querying over raw database schemas.
- Hands-on Technical Depth: Demonstrated comfort working directly with technical artifacts—inspecting retrieval traces, reading SQL query plans, reviewing JSON/YAML configurations, and executing API calls.
- AI Evaluation & Benchmarking: Proven track record of designing and running evaluation harnesses, golden benchmark datasets, error taxonomies, and quantitative quality gates.
- Security & Governance: Solid working knowledge of enterprise controls, including authentication/identity, tenant isolation, Row-Level Security (RLS), audit logging, and data privacy.
- Communication & Influence: Exceptional written and verbal communication skills in English, with a demonstrated ability to align and influence global engineering, security, compliance, and executive stakeholders without direct authority.
What will give you an edge:
- Experience with Knowledge Graphs, ontologies, taxonomies, and enterprise entity resolution (MDM).
- Hands-on familiarity with headless BI, metric stores (e.g., dbt Semantic Layer, Cube), or governed NL-to-SQL products.
- Domain background in payments, fintech, benefits, healthcare-adjacent platforms, or other highly regulated environments.
- Experience with vector databases, automated RAG evaluation frameworks (e.g., Ragas, TruLens), or agent tool protocols (e.g., Model Context Protocol - MCP).
- Proven track record of consolidating or replacing legacy enterprise knowledge management or search systems in active production.