Applied AI Engineer

Job Description

Job Description

DEPARTMENT:

Product: Engineering

POSITION:

Applied AI Engineer 

REPORTS TO:

Team Lead, Software Engineering

SUPERVISES:

None

JOB CLASS:

Exempt

PURPOSE:

We’re building the next generation of AI-powered experiences to support participants on their health journey, helping them achieve sustainable weight loss through meaningful behavioral change and guided, personalized experiences powered by applied AI. We’re looking for an Applied AI Engineer to help bring that vision to life by building and evolving our agent platform across orchestration, tool use, retrieval, safety, escalation, evaluation, and observability.

Beyond the product, you’ll build AI automation for our engineering team, including agents and workflows that accelerate development, testing, code review, and delivery. If you see a repetitive engineering task, you’ll be expected to automate it.

This role will be focused on building and evolving enterprise AI systems, not research prototypes. We’re looking for someone who has shipped production agent systems and understands real-world challenges such as memory, evals, compaction, safety and control, and multi-agent orchestration. Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or equivalent in-house systems is a plus.

ESSENTIAL FUNCTIONS :

• Develop and maintain LLM agent systems using AWS Bedrock, LangChain, and LangSmith, with transferable experience from comparable tools and frameworks.
• Build and contribute to core agent capabilities, including tool use for knowledge retrieval, ticketing, and onboarding flows, agentic loops, and human-in-the-loop interactions.
• Develop and improve memory and context systems, including conversation history, participant memory, and summarization for long-running interactions.
• Develop and evolve multi-agent and sub-agent systems using explicit state and orchestration rather than prompt sprawl.
• Implement and tune safety-critical flows, including guardrails, adversarial handling, escalation routing, and lockout logic.
• Build AI automation tools for engineering workflows, including code review assistance, testing automation, documentation generation, CI/CD intelligence, and developer productivity tools.
• Champion agentic development practices and help other engineers adopt AI-assisted workflows.
• Implement end-to-end tracing and evaluation so every request, node, LLM call, and tool call is observable and easy to debug.
• Manage model selection and cost/latency trade-offs, including prompt caching and routing to smaller models where appropriate.
• Integrate agent systems with platform services and third-party tools, including support systems, vector databases, API gateways, and mobile/web clients.
• Author technical design documents for new agent capabilities and contribute to architecture decisions.
• Write clean, testable code and participate in code reviews.
• Demonstrable hands-on experience building and operating production LLM/agent systems, with experience in at least few of the following: memory and context management, conversation summarization, workflow orchestration, or escalation.
• Hands-on experience with LLM evaluation methods, including automated evals, LLM-as-a-judge, and regression testing.
• Experience with RAG pipelines: vector databases (any, such as Pinecone, pgvector, OpenSearch, Weaviate), embedding strategies, and retrieval quality tuning
• Working knowledge of at least one major cloud platform (AWS, GCP, or Azure) and managed LLM services (e.g., Bedrock, Vertex AI, Azure OpenAI). We use AWS, but experience across platforms is transferable.
• Experience building safety and reliability mechanisms for LLM systems, including guardrails, adversarial handling, escalation paths, and failure modes.
• Enthusiasm for AI-assisted engineering workflows and hands-on use of agentic coding tools to improve developer productivity through automation.
• Strong communication skills. You can write clear technical design documents and explain trade-offs to both technical and non-technical teammates.
• A systems-thinking mindset: you consider token cost, latency, reliability, failure modes, and user trust beyond just whether a demo works.
• Operate production agent systems, including observability, incident response, debugging, evaluation, and continuous improvement.
• Direct experience with AWS Bedrock, LLMs including open-source models, LangChain/LangGraph, and LangSmith.
• Experience with LLM observability and tracing in production systems.
• Experience building internal developer tools or automation (e.g., AI-assisted code review, test generation, CI/CD bots, documentation pipelines).
• Experience in health tech or other high-trust, safety-sensitive domains (e.g., crisis handling, PHI, compliance-aware systems).
• Frontend experience with Vue or React Native.

KNOWLEDGE, SKILLS, AND ABILITIES:

Required:

• 3–5 years of solid backend engineering experience in a production environment, using Python or a similar programming language.

  Additional experience that is a plus:

• Direct experience with AWS Bedrock, LLMs including open-source models, LangChain/LangGraph, and LangSmith.
• Experience with LLM observability and tracing in production systems.
• Experience building internal developer tools or automation (e.g., AI-assisted code review, test generation, CI/CD bots, documentation pipelines).
• Experience in health tech or other high-trust, safety-sensitive domains (e.g., crisis handling, PHI, compliance-aware systems).
• Frontend experience with Vue or React Native. 

WHAT SUCCESS LOOKS LIKE:

In your first 30 days: You’re onboarded, shipping small PRs against the agent platform, contributing to code reviews, and tracing production conversations end-to-end to build context on how the agent works today.

By 90 days: Contribute to agent capabilities end-to-end and participate in technical design discussions and documentation.

By 6 months: You’ll contribute to architecture decisions with guidance from senior engineers, with a path toward owning them, and ship internal AI tooling used by the engineering team.

WHY WONDR:

• Mission that matters. The code you write directly affects people’s health outcomes.
• Build the AI platform powering Wondr’s next generation of AI experiences, from agent orchestration and memory to tools, safety, and observability.
• High-impact engineering. Solve challenging problems at the intersection of AI and production engineering, with the opportunity to see your work reach real participants.
• Shape how we build. Help establish the patterns, tooling, and engineering practices that will define how we build and operate AI systems at Wondr.
• Fully remote. Work from wherever you do your best thinking.
• Growth opportunity. You'll have a clear path from strong mid-level contributor to senior engineer with system design ownership.
• Collaborative culture. Small team, low ego, high trust.

DISCLAIMER:

This description is intended to be sufficient merely to identify the classification and be illustrative of the duties that may be assigned. It should not be interpreted to describe all the duties an employee assigned to this classification may be required to perform.

Wondr Health is an equal opportunity employer and values diversity. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran, or disability status. All employment is decided based on qualifications, merit, and business need. Wondr Health also participates in E-Verify and will provide the federal government with your Form I-9 information to confirm that you are authorized to work in the U.S.

This description is intended to be sufficient merely to identify the classification and be illustrative of the duties that may be assigned. It should not be interpreted to describe all the duties an employee assigned to this classification may be required to perform.

Wondr Health is an equal opportunity employer and values diversity. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran, or disability status. All employment is decided based on qualifications, merit, and business need.