Lead AI Engineer, Agentic AI Solutions

Bridgewater, NJ hybrid role focused on delivering production-grade, agentic AI solutions that support commercial decision-making.

Responsibilities

• Design, build, and operate production Applied agents across the commercial process: brand strategy, customer insights, personalized engagement, and closed-loop feedback, using foundational agents rather than rebuilding.
• Build performance investigation agents that autonomously decompose brand performance shifts across geography, channel, payer, and Eye Care Professional (ECP) segment; return sourced, reproducible narratives for brand and insights teams.
• Build pre-call, post-call, and next-best-action / next-best-engagement agents that assemble ECP briefs from Glimpse (Next Best Action) platform and/or CRM; attach explainable reasoning to recommendations and write structured data back to CRM.
• Build measurement and feedback agents to support A/B and multivariate test design, readout, and write-back into the planning loop.
• Ground agents in the enterprise semantic layer and commercial knowledge graph so metric definitions, joins, grain, and row- and role-level access are resolved prior to query generation.
• Implement determinism and reproducibility controls, including validate-then-lock specification patterns, ensuring repeated runs produce the same results for auditable decisions.
• Integrate agents with enterprise systems including Glimpse (NBA platform) / Veeva or Salesforce, Adobe, and internal commercial platforms using Model Context Protocol (MCP), agent-to-agent (A2A) patterns, tool discovery, scoped authentication, and structured outputs.
• Create and maintain agent evaluation harnesses: golden datasets, calibrated LLM-as-judge scoring, and regression testing; track agent KPIs for task completion, grounding, reproducibility, human-override rate, latency, and cost per task.
• Operate with bounded autonomy: agents prepare, propose, investigate, summarize, and route while humans in the loop approve claims, privacy-sensitive actions, and validated-record changes.
• Own production operations including observability and tracing, Evals, token and cost controls (loop caps, model routing and fallback, latency budgets), versioning, rollback, on-call response, and postmortems.
• Partner with Medical, Legal, Regulatory, Privacy, Compliance, and IT to incorporate Responsible AI standards during design.
• Collaborate with brand teams, field operations, market access, and commercial analytics to translate business asks into agent specifications tied to a defined decision; decline use cases where an agent is the wrong tool.
• Participate in Agile AI Operations: backlog management, sprint planning, cross-functional collaboration, and continuous improvement.
• Contribute reusable patterns, components, and documentation to a shared agent pattern library; mentor engineers and analysts adopting them.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Engineering, or a related field.
• 5+ years of experience building and deploying production software, AI, or ML solutions, including LLM-powered applications.
• Strong Python development and software engineering best practices: testing, CI/CD, APIs, code reviews, and containerization.
• Hands-on experience with AI agent frameworks such as LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, or similar.
• Experience with tool calling, structured outputs, function schemas, and enterprise system integrations.
• Experience designing and implementing RAG solutions, vector databases, embeddings, and retrieval systems.
• Strong SQL and data modeling skills, including defining and validating business metrics.
• Experience developing frameworks and metrics to evaluate AI/LLM performance.
• Experience with cloud and MLOps platforms such as AWS, Azure, Databricks, Snowflake, and orchestration tools.
• Experience operating in regulated environments with governance, compliance, and auditability focus.
• Proven ability to collaborate effectively across technical and business functions.
• Experience working in Agile environments using Scrum, SAFe, or similar methodologies.
• Strong communication and presentation skills for non-technical audiences.

Preferred

• Experience with pharmaceutical, medical device, or consumer health commercial data, including prescription, claims, payer, CRM, and sales data.
• Familiarity with eye care industry dynamics (ophthalmology, optometry, and ECP channels).
• Experience with Veeva and/or Salesforce integrations.
• Experience with knowledge graphs, semantic modeling, and semantic layer tools.
• Familiarity with healthcare compliance requirements including HIPAA, GDPR, FDA promotional regulations, and MLR/PRC review processes.
• Experience with LLM observability, monitoring, and AI cost management.
• Experience in regulated industries with strong governance, auditability, and compliance requirements.

Technology

• Python
• Azure / AWS, Databricks, Snowflake
• LLMs, Agentic AI
• RAG, vector databases, embeddings, retrieval systems
• Salesforce, Veeva, CRM, Adobe, Glimpse
• LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex
• Model Context Protocol (MCP), model routing, A2A patterns, tool discovery, structured outputs, function schemas
• Knowledge graphs, semantic layer
• SQL, CI/CD, A/B testing, multivariate testing
• Evals, containerization, MLOps
• Scrum, SAFe

Benefits

• Medical, dental, vision insurance
• Disability and life insurance
• 401(k) plan and company match
• Tuition reimbursement program (select degrees)
• Company holidays
• Well-being benefits
• Sick time
• Floating holidays
• Paid vacation
• U.S. based employees may be eligible for short-term and/or long-term incentives

Location and Work Model

• Bridgewater, NJ (hybrid)
• Eligible for hybrid schedule allowing up to 2 days/week telecommuting and 3 days/week in the Bridgewater, NJ corporate office

Compensation

• USD 150,000 - 200,000 per year (starting pay range)
• Actual base salary may vary based on factors; estimated range reflects anticipated range for the position

Authorization to Work

• Applicants must be authorized to work for any employer in the U.S.
• Company is unable to sponsor or take over sponsorship of an employment Visa at this time