Assured Allies is a mission-driven startup dedicated to helping older adults age successfully - financially, socially, and independently. We combine deep expertise in insurance, health, and wellness with cutting-edge data and AI technology to build scalable, impactful products. As part of this mission, we are now developing AI-driven health coaching models that can personalize guidance, generate high-quality wellness content, and make effective health support accessible to millions of users. With a rich foundation of clinical and behavioral data, we are designing internal models and agentic systems that will power our next generation of wellness experiences.

We are looking for a practical, hands-on Senior AI Agent Engineer with a strong engineering foundation and deep recent experience in LLMs, AI systems, and agent architectures. This role is ideal for someone who thrives on building from scratch - collaborating closely with product, designing robust guardrails and evaluation processes, and shaping AI capabilities end-to-end.

This is the first dedicated AI Agent Engineering function within our team, offering a unique opportunity to lead and define this domain. As an Senior AI Agent Engineer, you will design, implement, and maintain advanced agentic systems built on top of leading LLMs such as OpenAI, Claude, Gemini, and open-source models. You will play a central role in architecting the underlying infrastructure, defining agent behavior, and ensuring reliability, safety, and observability, while partnering across teams to deliver high-impact AI capabilities throughout the organization.

Your responsibilities will span the entire lifecycle of our AI agents, from choosing the foundational infrastructure to implementation, monitoring in production, development, and continuous evaluation.

What You'll Do:

Agent & LLM Development

• Design and develop personalized health coach agents on top of LLMs (OpenAI, Claude, Gemini, open-source).
• Implement and operate agent frameworks (ADK, LangGraph, AutoGen, CrewAI).
• Write and optimize advanced prompts, system instructions, and multi-step agent workflows.
• Build supporting backend and infrastructure components (APIs, orchestration layers, integrations).

Guardrails, Evaluation & Reliability

• Define and enforce guardrails, safety policies, and behavioral constraints for agents.
• Build evaluation pipelines, monitoring tools, and performance metrics.
• Continuously test, refine, and improve agent reliability, safety, and consistency.
• Ensure observability, logging, and debuggability across agent workflows.

Product Collaboration

• Work closely with product managers to understand use cases and translate business goals into technical agentic solutions.
• Collaborate with data, engineering, and operations teams to deploy production-ready systems.
• Participate in shaping new AI-driven workflows, capabilities, and customer-facing features.

What We're Looking For:

• 7+ years of experience in backend or fullstack engineering (Python/Node/Java, etc.).
• 2+ years of hands-on experience building LLM-based applications or systems.
• Ability to build AI infrastructure and backend systems from scratch, including data ingestion, API integrations, and event-driven components.
• Strong familiarity with agent architectures and workflow orchestration, including dynamic context/memory management and RAG over structured and unstructured data.
• Demonstrated ability to design guardrails, evaluation processes, and monitoring workflows.
• Strong product intuition and ability to partner closely with non-technical stakeholders.

Why Join Us?

• Build from zero: shape the architecture and capabilities of Assured Allies’ next-generation AI systems.
• Direct impact on product and end-user experience.
• Mission-driven work that improves the lives of older adults.
• Fast-moving environment with autonomy, ownership, and room to innovate.