• Design and deliver AI-driven systems that power features used by millions of users • Build scalable AI systems that connect models, data, and products • Turn research prototypes into reliable, production-ready services • Build pipelines and serving layers that power adaptive, real-time features • Collaborate with other engineering teams to ensure performance and reliability • Create reusable SDKs and libraries that accelerate AI adoption

• Lead development of cloud-based Python applications that integrate AI/ML (GenAI, predictive models, NLP) capabilities using frameworks like LangChain • Build LLM-powered agents using modern agentic frameworks such as LangChain, LlamaIndex, or CrewAI to enable advanced automation and reasoning capabilities in Mindoula's behavioral health technology platform • Collaborate with data scientists to turn models into robust, scalable APIs and user-facing tools • Design and implement application features that enable care teams to engage members more effectively using AI-driven insights • Architect secure, performant backend services and databases in a HIPAA-compliant environment • Ensure robust DevOps, testing, and monitoring pipelines for AI features in production • Translate clinical, business, and user requirements into full-stack solutions, balancing speed, safety/governance, and sustainability • Establish processes for human-in-the-loop feedback, governance, and review cycles to ensure AI applications remain safe, ethical, and aligned with clinical, business, and user needs • Contribute to build vs. buy/license decisions by evaluating technology options, defining criteria, and advising on trade-offs for AI applications • Document development patterns, model interfaces, and deployment pipelines to support collaboration and continuity • Participate in agile ceremonies, sprint planning, and cross-functional brainstorms with product, clinical, and operations teams

• Work with the latest technologies across an incredibly diverse portfolio of client challenges • Operate at the intersection of client mission delivery and internal product innovation • Lead diverse, high-caliber engineering teams across constantly evolving projects—no two months look the same • Mentor brilliant engineers while learning from domain experts across industries, from pharmaceutical researchers to Wall Street quants • Drive technical decisions on projects that span from 2-week rapid prototypes to 6-month platform overhauls • Collaborate with our internal AI research team to translate breakthrough academic papers into client solutions • Build your reputation as a go-to architect for impossible AI challenges • Jump between internal R&D and client missions, ensuring you're always working on the most technically interesting challenges • Extract breakthrough patterns from client work to build the next generation of AI infrastructure that other companies will struggle to replicate • See your architectural decisions impact Fortune 500 companies within weeks, not years • Access exclusive partnerships with AI research labs and get early preview access to models before they're publicly available

• Design for Action: Build AI integrations that do more than just summarize text. Design systems that can securely read from and write back to our core platforms (e.g., updating a record in Salesforce or drafting a response in Zendesk). • Secure Data Flow: Architect the integration layer between external LLM providers (Google, Anthropic, OpenAI) and internal data. Ensure all data retrieval is governed by strict permissions so users are only able to access data they are authorized to see. • Scalability: Design a model-agnostic inference layer that allows us to switch between models based on performance and cost requirements. • Backend Engineering: Write production-ready code using modern agent frameworks (ADK, LangChain). This is a technical role that requires coding. • Retrieval Augmented Generation (RAG): Implement robust RAG pipelines to ground AI responses in company data. This includes managing vector databases and optimizing search strategies (hybrid search, reranking) to ensure accuracy. • Deployment: Set up the CI/CD pipelines and infrastructure required to deploy and maintain these services in a cloud environment. • Evaluation: Move beyond "eye-balling" results. Implement automated testing frameworks to measure response accuracy, latency, and costs before deploying changes. • Data Privacy: Ensure strict handling of PII and adherence to enterprise security standards. You will be the gatekeeper for how sensitive data is exposed to LLMs. • Requirements Gathering: Partner with leaders in Sales, Marketing, and Support to identify high-impact automation opportunities. Translate business needs into technical specifications.