Staff AI/Agentic Engineer

At Abbott, you can do work that matters, grow, and learn, care for yourself and your family, be your true self, and live a full life. You’ll also have access to:

• Career development with an international company where you can grow the career you dream of.
• Employees can qualify for free medical coverage in our Health Investment Plan (HIP) PPO medical plan in the next calendar year.
• An excellent retirement savings plan with a high employer contribution
• Tuition reimbursement, the Freedom 2 Save student debt program, and FreeU education benefit - an affordable and convenient path to getting a bachelor’s degree.
• A company recognized as a great place to work in dozens of countries worldwide and named one of the most admired companies in the world by Fortune.
• A company that is recognized as one of the best big companies to work for as well as the best place to work for diversity, working mothers, female executives, and scientists.

A senior individual-contributor engineering role that sets technical direction for production agentic systems at Abbott. This role leads the design of complex multi-agent solutions and reusable engineering patterns, partners closely with the Tech Lead/Architect on architecture decisions and is a primary technical escalation point across the AI/Agentic Engineering team. Expected to operate with substantial autonomy and to raise the technical bar for the team.

• →Lead design and implementation of complex multi-agent systems, including supervisor, planner/executor, and multi-agent coordination patterns with well-defined boundaries and failure handling.
• →Set standards for durable workflow design (state, checkpoints, replay, idempotency, compensation, human-in-the-loop) used across the AI/Agentic Engineering team.
• →Drive context-engineering and retrieval strategy across multiple workflows: chunking/indexing, memory hierarchies, grounding, and context-window budgeting.
• →Lead evaluation strategy: design evaluation systems, curate datasets, define task-success and safety metrics, and establish regression gates in CI and online/shadow evaluation.
• →Own production reliability for high-complexity or high-risk agentic systems: latency/cost optimization at scale, rate-limit strategy, graceful degradation, and incident response leadership.
• →Set engineering standards through architecture reviews, design docs, and code reviews; identify and resolve systemic technical risk in agent delivery.
• →Create reusable agent patterns, SDKs, and evaluation tooling that feed back into the platform paved road, in partnership with AI Platform Engineering.
• →Lead technical discovery with AI Product Managers, Platform Engineering, Applied Data Science, and business stakeholders; communicate feasibility, risk, and delivery commitments directly to senior stakeholders.
• →Mentor and technically develop mid-level and junior engineers; act as technical lead on cross-team initiatives without formal people-management responsibility.

• 7–10 years of software engineering experience, with substantial delivery of distributed, API-driven, or workflow-intensive production systems.
• Hands-on experience designing, coding, testing, deploying, and operating agentic or LLM-based applications in production at scale; expected to remain an active technical contributor.
• Deep 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 distributed systems, API design, testing, and secure SDLC.
• Experience defining measurable quality, safety, reliability, latency, and cost indicators and using evaluation results to drive systemic improvement across multiple workflows.
• Bachelor's degree in a related field or equivalent professional experience.
• Demonstrated ability to drive technical decisions with significant autonomy, influence engineers outside a direct reporting line, and communicate effectively with technical leadership.

• Experience with agent frameworks or durable workflow systems (e.g., LangGraph, Temporal, or comparable technologies) and model-provider APIs at scale.
• Experience in a highly regulated environment such as health tech, med-tech, or life sciences, including GxP, HIPAA, validation, and change-control constraints.
• Experience building secure tool-use systems, prompt-injection defenses, human-approval workflows, and responsible-AI controls for production agentic systems.
• Track record of shipping reusable agent patterns, evaluation tooling, or paved-road capabilities adopted by multiple teams; prior informal technical leadership or mentoring track record.