Lead Engineer - Agentic AI

We are looking for passionate and driven professionals to join Data. Zymes, a next-generation analytics and data science company founded in 2016. At Data. Zymes, we focus on driving technology-led innovation and helping clients maximize the value of their data and analytics investments through cutting-edge platforms and consulting expertise.

If you are excited about working on impactful solutions in the healthcare analytics space and want to be part of a high-performance, fast-growing team, we’d love to hear from you. We are a data and analytics services firm purpose-built for the pharmaceutical and life sciences industry. Our clients span commercial analytics, medical affairs, real-world evidence, and clinical operations.

We are now building the capability that will define the next phase of this business: production-grade agentic AI embedded in the workflows our clients rely on daily. This role is not a strategy position. It is not a research position. It is a builder-leader role. You will architect and ship multi-agent systems that operate autonomously across pharma data pipelines, regulatory intelligence workflows, and cross-functional analytics use cases.

You will write code, own production deployments, and lead a small team doing the same. The ideal candidate has deep technical fluency in agentic frameworks, understands the compliance, data governance, and validation expectations of the pharma industry, and can translate both into working systems, not slide decks.

Requirements

• Design and build end-to-end agentic systems combining LLMs, multi-agent orchestration, enterprise data pipelines, and pharma-specific business logic. Ship production-grade systems, not prototypes.
• Select and implement the right orchestration approach across no-code, low-code, and pro-code patterns based on use case complexity and client readiness.
• Architect retrieval and knowledge services (RAG, knowledge graphs) over structured and unstructured pharma data: Rx, claims, engagement, clinical trial data, RWE datasets, label text, and scientific literature. Includes RAG pipelines, knowledge graphs for entity-relationship modeling (HCP, drug, indication, trial networks), hybrid search, and retrieval evaluation frameworks.
• Build observability, monitoring, and evaluation frameworks to track agent behavior in production. Define guardrails, failure modes, and human-in-the-loop escalation points.
• Integrate with upstream pharma data platforms (IQVIA, Symphony, Komodo, Veeva) and downstream delivery surfaces via APIs and workflow hooks. PHARMA DOMAIN APPLICATION
• Translate commercial analytics, medical affairs, and clinical operations workflows into agentic automation opportunities. Target high-volume, high-complexity, logic-intensive processes first.
• Build agents that operate over 21 CFR Part 11-aware environments. Understand what auditability, validation, and traceability mean for autonomous systems in a regulated context.
• Develop intelligent document processing pipelines for clinical study reports, drug labels, HEOR submissions, and payer dossiers.
• Apply agentic AI to KOL identification and mapping, literature synthesis, competitive intelligence, and signal detection workflows. LEADERSHIP & CLIENT DELIVERY
• Lead a team of AI engineers and ML practitioners. Set technical direction, review architecture decisions, and maintain a high bar for production quality.
• Partner with client-facing teams to scope agentic AI engagements: define the use case, design the solution architecture, and own delivery accountability.
• Communicate complex agent system behavior to non-technical pharma stakeholders. Bridge the gap between what agents do and what the business needs to trust.
• Champion AI governance practices aligned with industry standards: documented agent decision logic, bias audits, and traceability to source data.
• Build internal capability by mentoring team members and establishing the firm's agentic AI playbook as a reusable asset. What You Bring TECHNICAL DEPTH (REQUIRED)
• 8+ years in software or ML engineering; 3+ years with production LLM or agentic AI systems.
• Hands-on proficiency with agentic frameworks: Lang. Graph, Lang. Chain, Auto. Gen, CrewAI, or equivalent. Model Context Protocol (MCP) familiarity strongly preferred.
• Direct SDK experience: Anthropic (Agents SDK, tool use, Claude API), OpenAI (Assistants API, function calling), Google (Vertex AI Agent Builder, Gemini API). Model Context Protocol (MCP) strongly preferred.
• Python fluency. Ability to build, test, and deploy production code, not just notebooks.
• Strong RAG architecture skills: chunking strategies, embedding models, vector stores, knowledge graphs for entity-relationship modeling (drug-indication-HCP-trial), hybrid search, retrieval evaluation.
• Cloud-native deployment: AWS, Azure, or GCP. Containerization (Docker, Kubernetes), CI/CD, infrastructure-as-code.
• Observability tooling for AI systems: logging agent traces, eval frameworks, cost management, drift detection. PHARMA / LIFE SCIENCES DOMAIN (REQUIRED)
• Working knowledge of pharma commercial data ecosystems: Rx/claims data, NPI-level analytics, market access, brand performance
• Familiarity with regulated data environments: GxP, 21 CFR Part 11, HIPAA-compliant data handling, audit trail requirements
• Exposure to at least two of: medical affairs analytics, real-world evidence, clinical operations data, or HEOR/market access workflows
• Comfort reading and reasoning over scientific and regulatory documents: labels, clinical study reports, AMCP dossiers, payer briefs LEADERSHIP & COMMUNICATION (REQUIRED)
• 5+ years leading technical teams or delivery workstreams, including mentoring engineers and managing project scope and timelines
• Track record of shipping production AI solutions with measurable business impact, not just proof-of-concepts
• Comfortable in executive-level conversations: scoping engagements, presenting architecture trade-offs, and aligning on governance expectations
• Strong written communication. You can write a crisp technical spec and a clear client-facing proposal without switching tools GOOD TO HAVE
• Experience with Veeva Vault, Medidata, or IQVIA platform integrations
• Knowledge of reinforcement learning from human feedback (RLHF) and fine-tuning workflows
• Familiarity with EU AI Act and emerging FDA guidance on AI/ML in clinical and regulatory contexts
• Prior consulting or services-firm experience: multi-client delivery, proposal development, engagement management