Principal AI/Agentic Engineer

About Abbott 

About Abbott (standard corporate boilerplate; pull the current approved version from Talent Acquisition/Brand before external use): Abbott is a global healthcare leader that helps people live more fully at all stages of life. Our portfolio spans diagnostics, medical devices, nutritionals, and branded generic medicines, and our colleagues serve people in more than 160 countries.

The Opportunity 

A hands-on software engineering leadership role accountable for building production-grade agentic systems on Abbott's enterprise AI Platform. This role turns business and product requirements into reliable single- and multi-agent solutions, reusable engineering patterns, and measurable outcomes. The role is Director-mapped and begins as a player-coach: it leads delivery and technical standards while building and managing a team of agentic engineers. 

What You'll Do 

•  Design, implement, and operate production agentic systems, including supervisor, planner/executor, and multi-agent patterns with explicit boundaries, failure handling, and human oversight. 

•  Build durable, resumable workflows with persistent state, checkpoints, replay, idempotency, compensation, and human-in-the-loop controls (e.g., LangGraph- or Temporal-style durable execution). 

•  Engineer tool and function integrations with Abbott enterprise systems, including MCP-style tool contracts, schemas, authorization, retries, timeouts, compensation, and failure containment. 

•  Develop context-engineering strategies covering retrieval, chunking and indexing, memory hierarchies, context-window budgeting, caching, structured outputs, and grounding. 

•  Create evaluation systems with curated datasets, task-success and safety metrics, LLM-as-judge and programmatic evaluators, regression gates in CI, and online, A/B, and shadow evaluation. 

•  Instrument agent applications through the platform's model and agent registries and tracing services so prompts, tool calls, intermediate steps, quality, cost, and latency are observable and auditable.

•  Engineer for production reliability: streaming, concurrency, latency and token-cost optimization, rate limits, graceful degradation, secure deployment, SLOs, on-call, incident response, and rollback of agent regressions. 

•  Write and review substantial production code in Python and at least one of TypeScript, Go, or Java; establish testing, code review, API design, and secure software engineering practices. 

•  Lead technical discovery and delivery with AI Product Managers, Platform Engineering, Applied Data Science, security, and business stakeholders; communicate feasibility, risks, and delivery commitments. 

•  Hire, coach, and develop a team of approximately 3–8 agentic engineers; set goals, allocate work, review performance, and create reusable patterns that feed back into the platform paved road. 

Required Qualifications 

•  10–15+ years of software engineering experience, including substantial delivery of distributed, API-driven, or workflow-intensive production systems and technical leadership. 

•  Hands-on experience designing, coding, testing, deploying, and operating agentic or LLM-based applications in production; this role is expected to remain an active technical contributor. 

•  Strong understanding of agent architecture, tool calling, durable state, multi-agent coordination, context engineering, retrieval, evaluation, observability, and safety controls. 

•  Strong software engineering ability in Python and at least one of TypeScript, Go, or Java, including APIs, distributed systems, CI/CD, testing, code review, and secure SDLC. 

•  Experience defining measurable quality, safety, reliability, latency, and cost indicators and using evaluation results to improve systems through iterative releases. 

•  Bachelor's degree in a related field or equivalent professional experience. 

•  Demonstrated ability to lead engineers, make sound technical decisions under uncertainty, and communicate effectively with technical and non-technical stakeholders. 

Preferred Qualifications 

•  Experience with agent frameworks or durable workflow systems (e.g., LangGraph, Temporal, or comparable technologies) and model-provider APIs. 

•  Experience in a highly regulated environment such as health tech, med-tech, or life sciences, including GxP, HIPAA, validation, auditability, and change-control constraints. 

•  Experience building secure tool-use systems, prompt-injection defenses, human-approval workflows, responsible-AI controls, and privacy-preserving agent experiences. 

•  Experience shipping reusable agent patterns, evaluation tooling, SDKs, or paved-road capabilities for multiple product or engineering teams. 

In specific locations, the pay range may vary from the range posted.