Join an inclusive, collaborative Business Technology Solutions (BTS) team as a
Sr Engineer, Applied AI & Engineering Platforms at AbbVie. This is a hands-on, lead technical engineering role at the center of AbbVie's generative and agentic AI transformation - building intelligent, autonomous systems and scalable agentic workflows that will accelerate drug discovery, streamline clinical and regulatory operations, and reimagine how AbbVie works across every function.
You will design and own the AI foundations layer that underpins all agentic capabilities across the enterprise, establish engineering standards that make AI systems reliable and auditable in GxP-regulated environments, and serve as a technical authority guiding platform teams, data scientists, and application engineers across the organization.
This is not a research or prototyping role. You will architect, build, and operate production-grade multi-agent systems used in clinical, commercial, and operational domains - working alongside enterprise architecture, platform security, data engineering, MLOps, and domain subject matter experts to ensure every system is deployable, governed, and compliant from day one.
Responsibilities:
Agentic System Design & Engineering
- Architect and own production-grade multi-agent systems using orchestration frameworks (LangChain, LangGraph, CrewAI, OpenAI Agents SDK, AutoGen/AG2, Semantic Kernel), making deliberate decisions on state management, routing, memory architecture, and failure handling.
- Design agent cognitive architectures - planning loops (ReAct, Reflexion, CoT), tool-use patterns, memory systems (short-term, episodic, semantic), and self-evaluation loops.
- Build multi-agent coordination patterns (supervisor-worker, peer collaboration, A2A protocols) aligned with emerging open standards including MCP server integration to connect agents to enterprise systems, clinical data platforms, and regulatory repositories.
AI Foundations Layer
- Design and maintain shared AI infrastructure: LLM gateway/routing, embedding services, vector stores, RAG pipelines, prompt management, and model evaluation harnesses across all agentic products.
- Establish model selection and governance spanning hosted providers (Claude, GPT, Gemini) and self-hosted models, including fine-tuning pipelines (LoRA/QLoRA) for pharmaceutical-specific tasks.
- Build context engineering standards - managing context windows, retrieval strategies, chunking, re-ranking, hybrid search, and query routing for enterprise-scale clinical and scientific knowledge - with guardrails, safety layers, content filters, and HITL escalation appropriate for GxP environments.
Agentic Engineering SDLC
- Define the end-to-end SDLC for agentic systems - from design through evaluation, deployment, and continuous monitoring - treating agent behavior as a first-class software artifact subject to change control.
- Build agent evaluation frameworks (golden test sets, LLM-as-judge scoring, regression detection, task-completion benchmarks, latency/cost dashboards) and CI/CD pipelines with automated evaluation gates, drift detection, and rollback capabilities.
- Establish traceability, audit logging, and versioning standards supporting GxP validation, 21 CFR Part 11, and AbbVie's AI governance policy.
Observability, Reliability & AIOps
- Implement full-stack observability (LangSmith, Langfuse, OpenTelemetry): trace-level logging, token/cost tracking, latency profiling, and anomaly detection on agent behavior.
- Own production reliability - retry logic, fallback strategies, circuit breakers, graceful degradation, and HITL escalation for regulated workflows. Monitor for behavior drift and decision inconsistency; implement continuous feedback loops without introducing regressions.
- Integrate agentic services with enterprise platforms (Salesforce, MuleSoft, Veeva, SAP, Databricks, ServiceNow) using MCP and standardized API patterns.
Governance, Compliance & Responsible AI
- Design agent authorization models operationalizing AbbVie's AI risk tiers (HIGH/LOW), defining what agents can access, act on, and decide autonomously versus what requires human approval.
- Implement governance controls aligned with FDA AI/ML guidance, ICH E6/E8, EU AI Act, and AbbVie internal policy - ensuring compliance with data residency, privacy (HIPAA, GDPR), least-privilege access, prompt injection defense, and secure MCP/A2A integrations.
- Build validation artifacts satisfying audit requirements for agents in clinical, regulatory, and GxP-controlled workflows.
Cross-Functional Technical Leadership
- Partner with product managers, data scientists, enterprise architects, platform security, and domain teams to translate pharmaceutical problems into agent system designs; define reusable patterns and shared platform components that accelerate development across teams.
- Mentor engineers on the agentic AI platform, conduct architecture reviews, establish engineering standards, and foster a culture of production-quality AI development while driving adoption of emerging standards (MCP, A2A, evaluation benchmarks) relevant to AbbVie's environment.
Qualifications
Required:
- Minimum years of experience: 6+ with Bachelors, or 5+ with Masters, or 0+ with PhD in software engineering with demonstrated depth in AI/ML systems, NLP/LLM applications, or production AI platforms - including experience building Generative AI or LLM-powered applications in production environments.
- Demonstrated hands-on experience architecting and deploying production-grade AI agent or multi-agent systems - not prototypes or POCs - using at least one major orchestration framework (LangChain, LangGraph, CrewAI, OpenAI Agents SDK, AutoGen/AG2, or Microsoft Semantic Kernel).
- Strong Python proficiency including async programming (asyncio), RESTful API design (FastAPI), system design patterns for scalable distributed AI systems, and production-quality coding practices.
- Hands-on experience building and operating RAG pipelines: embedding models, vector databases (e.g., pgvector, Pinecone, Azure AI Search), chunking strategies, hybrid retrieval, and retrieval evaluation. Familiarity with LlamaIndex or similar RAG frameworks is a plus.
- Experience with one or more cloud AI platforms (AWS Bedrock, Azure AI Foundry, or Google Vertex AI) including serverless inference and managed agent services.
- Solid understanding of prompt engineering at the system level: system prompt design, structured output formats, tool-call schemas, context engineering, and prompt versioning.
- Clear communication skills - ability to articulate agent architecture decisions, risk tradeoffs, and compliance implications to both technical engineers and non-technical business stakeholders.
Preferred:
- Working proficiency with LLMOps/AIOps tooling (LangSmith, Langfuse, MLflow, or equivalent) for agent observability, experiment tracking, and production monitoring.
- Experience designing and implementing agent evaluation frameworks including test dataset design, LLM-as-judge scoring, regression benchmarking, and responsible AI practices.
- Open-source contributions, published work, or conference presentations in agentic AI, multi-agent systems, LLM engineering, machine learning, or related areas.
- Strong experience with MCP (Model Context Protocol), A2A (Agent-to-Agent), or equivalent tool-integration and agent communication standards; TypeScript or Go proficiency for MCP server development or full-stack AI delivery.
- Experience in pharmaceutical, life sciences, biotech, or other regulated industry environments with exposure to GxP, 21 CFR Part 11, FDA AI/ML guidance, ICH E6/E8, or ISO 42001 standards.
- Hands-on experience integrating AI agents with enterprise platforms (Salesforce, Veeva Vault, SAP, ServiceNow, Databricks, MuleSoft) or processing multimodal clinical/scientific data.
- Background in distributed systems or microservices architecture (event-driven, serverless, Kubernetes); familiarity with Docker, container orchestration, PyTorch, or Hugging Face for model experimentation.
- AWS, Azure, or GCP professional-level certifications; familiarity with AI-assisted development workflows (Cursor AI, GitHub Copilot).
Additional Information
Applicable only to applicants applying to a position in any location with pay disclosure requirements under state or local law:
- The compensation range described below is the range of possible base pay compensation that the Company believes in good faith it will pay for this role at the time of this posting based on the job grade for this position. Individual compensation paid within this range will depend on many factors including geographic location, and we may ultimately pay more or less than the posted range. This range may be modified in the future.
- We offer a comprehensive package of benefits including paid time off (vacation, holidays, sick), medical/dental/vision insurance and 401(k) to eligible employees.
- This job is eligible to participate in our short-term incentive programs.
Note: No amount of pay is considered to be wages or compensation until such amount is earned, vested, and determinable. The amount and availability of any bonus, commission, incentive, benefits, or any other form of compensation and benefits that are allocable to a particular employee remains in the Company's sole and absolute discretion unless and until paid and may be modified at the Company's sole and absolute discretion, consistent with applicable law.
