Director, Agent Intelligence - HYBRID ROLE
Vertex Pharmaceuticals
June 27, 2026
Remote friendly (Boston, MA)
United States
IT
Hybrid (3 days/week in Boston office)
Key Duties and Responsibilities
- Design and operate Vertex’s agent memory layer (personal and organizational): retention, retrieval, conflict resolution, and classification policies.
- Define and steward the persona system (“personas as code”): versioning, review, composition, deployment workflows.
- Curate a skills catalog (atomic tools and higher-order compositions) with contracts, registry, and quality standards.
- Design, build, and deploy flagship enterprise AI agents using Snowflake Cortex AI, Databricks AI, and agent orchestration frameworks; use builds to harden underlying primitives.
- Define and maintain enterprise standards for orchestration, prompt libraries, persona definitions, tool-use patterns, and response quality.
- Set conversational UX quality bar (tone/persona, citations, error handling, escalation paths, transparency) and drive consistency.
- Govern reusable prompt and skill assets with documentation and contribution workflows.
Knowledge and Skills (Qualifications)
- 10+ years in data engineering, AI/ML, or advanced analytics; 3+ years in NLP systems, AI agent development, or conversational AI.
- Hands-on production agent building with LangChain, LangGraph, or similar.
- Enterprise experience with Snowflake (Cortex AI/Analyst/Search) and/or Databricks (Agent Bricks/AI Functions/Mosaic AI).
- Full-stack AI engineering across data prep, prompt engineering, orchestration, evaluation/testing, deployment, and monitoring.
- Experience designing agent memory/state and long-horizon retrieval with an underlying data model.
- Production operations experience (availability, monitoring, continuous improvement).
- Leadership and ability to communicate with executive stakeholders.
Preferred
- Pharma/life sciences domain experience.
- Experience designing reusable agent abstractions (persona frameworks, skill registries, tool catalogs).
- Familiarity with evaluation tooling (Braintrust, LangSmith, Mosaic AI Agent Evaluation, Arize, Ragas).
- Experience with model fine-tuning/distillation/post-training for domain adaptation.
Pay Range: $216,400–$324,600 (eligible for annual bonus and annual equity awards).
Key Duties and Responsibilities
- Design and operate Vertex’s agent memory layer (personal and organizational): retention, retrieval, conflict resolution, and classification policies.
- Define and steward the persona system (“personas as code”): versioning, review, composition, deployment workflows.
- Curate a skills catalog (atomic tools and higher-order compositions) with contracts, registry, and quality standards.
- Design, build, and deploy flagship enterprise AI agents using Snowflake Cortex AI, Databricks AI, and agent orchestration frameworks; use builds to harden underlying primitives.
- Define and maintain enterprise standards for orchestration, prompt libraries, persona definitions, tool-use patterns, and response quality.
- Set conversational UX quality bar (tone/persona, citations, error handling, escalation paths, transparency) and drive consistency.
- Govern reusable prompt and skill assets with documentation and contribution workflows.
Knowledge and Skills (Qualifications)
- 10+ years in data engineering, AI/ML, or advanced analytics; 3+ years in NLP systems, AI agent development, or conversational AI.
- Hands-on production agent building with LangChain, LangGraph, or similar.
- Enterprise experience with Snowflake (Cortex AI/Analyst/Search) and/or Databricks (Agent Bricks/AI Functions/Mosaic AI).
- Full-stack AI engineering across data prep, prompt engineering, orchestration, evaluation/testing, deployment, and monitoring.
- Experience designing agent memory/state and long-horizon retrieval with an underlying data model.
- Production operations experience (availability, monitoring, continuous improvement).
- Leadership and ability to communicate with executive stakeholders.
Preferred
- Pharma/life sciences domain experience.
- Experience designing reusable agent abstractions (persona frameworks, skill registries, tool catalogs).
- Familiarity with evaluation tooling (Braintrust, LangSmith, Mosaic AI Agent Evaluation, Arize, Ragas).
- Experience with model fine-tuning/distillation/post-training for domain adaptation.
Pay Range: $216,400–$324,600 (eligible for annual bonus and annual equity awards).