• Deliver phase-one AI capabilities in our existing Amazon Connect environment, focusing on AI-first call handling, intelligent routing, and autonomous resolution of common login, account, and password-reset queries. • Design AI-first workflows for voice and email that prioritize autonomous resolution, allowing the system to intelligently decide when to handle a request end-to-end and when to route to an agent. • Leverage our existing call recordings and transcripts to extract real interaction patterns and customer language to ground the AI in actual member needs. • Build elegant handoff patterns that preserve a member's interaction history, intent, and attempted actions so they never have to repeat themselves. • Write clean, production-ready Python backend code and AWS Lambda integrations to handle secure account lookups, validation, and CRM updates. • Integrate Amazon Connect workflows with HubSpot and other internal systems to equip the AI agent with real-time customer context. • Establish a reusable metadata and session strategy to enrich ongoing and future interactions with purchase history and communication logs. • Tune RAG (Retrieval-Augmented Generation) patterns and Bedrock Knowledge Bases to keep AI responses grounded in approved policies and procedures. • Implement practical guardrails that keep AI responses focused on approved topics and apply secure verification steps for sensitive workflows. • Deploy and manage AWS resources using CloudFormation, CDK, or Terraform, ensuring version-controlled deployments of Connect flow JSONs. • Author clean, clear architecture runbooks, deployment procedures, and prompt configurations to ensure the wider team can easily operate your work. • Lay the technical foundations for future authenticated transactions like billing updates, self-service cancellations, and payment processing.

Role Description We are looking for an exceptional AI Architect to design, build, and optimize AI-driven applications on the Azure platform. This role emphasizes strong engineering expertise, creative problem-solving, and the ability to work with cutting-edge technologies to deliver high-impact solutions. The ideal candidate thrives on solving complex challenges, is passionate about engineering excellence, and has a knack for integrating AI into scalable, real-world applications. A background in data science or formal engineering is a strong advantage, given the scientific nature of the work. Key Responsibilities - Architect & Build: Design and implement AI applications leveraging Azure services (AKS, Azure Container Apps, Blob Storage, Document Intelligence, AI Studio/Foundry, VNETs). - Full-Stack Development: Develop systems using C#, Python, React, and modern frameworks like Entity Framework Core, LangChain, Semantic Kernel, and FastAPI. - Scalable & Secure Solutions: Create applications that are resilient, secure, and optimized for high performance. - Collaboration: Work closely with cross-functional teams, including data scientists and engineers, to turn abstract ideas into functional solutions. - Cloud-Native Focus: Lead the deployment and optimization of applications in Azure environments with strong consideration for cost efficiency and maintainability. - Innovate & Optimize: Explore new tools, frameworks, and methodologies to stay at the forefront of AI and software engineering. Qualifications - Proven expertise in software engineering with experience in C#, Python, and React (TypeScript). - Hands-on experience with cloud platforms, particularly Azure, including services like AKS, Networking, and AI Studio/Foundry. - Familiarity with AI frameworks like LangChain, Semantic Kernel, and other AI libraries or tools, as well as techniques such as RAG, Agentic patterns, and workflow orchestration. - Strong grasp of modern development practices, such as containerization, CI/CD, and API design. - Demonstrated ability to design and build secure, scalable, and maintainable systems. Preferred Skills - Background in data science or formal training in engineering disciplines. - Experience with frameworks like Entity Framework Core, Material UI, and FastAPI. - Understanding of AI modeling workflows and integration of document intelligence or related tools. Core Qualities - Problem-Solving Excellence: A creative and analytical approach to tackling technical challenges. - Ownership & Accountability: Ability to take full responsibility for the design, implementation, and success of projects. - Adaptability: Comfortable learning and implementing new technologies in a fast-evolving field. - Team Collaboration: Strong communication skills and a mindset that thrives in a team-driven environment. Company Description Nimble Gravity is a team of outdoor enthusiasts, adrenaline seekers, and experienced growth hackers. We love solving hard problems and believe the right data can transform and propel growth for any organization. Nimble Gravity is an Equal Opportunity Employer and considers applicants for employment without regard to race, color, religion, sex, orientation, national origin, age, disability, genetics or any other basis forbidden under federal, state, or local law. Nimble Gravity considers all qualified applicants.

Role Description We’re looking for a Senior AI Engineer to join our Engineering team. This person will play a pivotal role in architecting and delivering privacy-first AI systems that power the next generation of Osano’s product capabilities. This role goes beyond wrapping APIs or building chat interfaces. You will: - Design and deploy autonomous AI agents - Develop strict-source-following RAG systems - Implement evaluation frameworks that ensure reliability, compliance, and production-grade performance This position is ideal for someone who is highly technical, thrives in ambiguity, takes ownership of 0→1 initiatives, and believes responsible AI development is non-negotiable. Responsibilities - AI System Architecture - Architect and deploy autonomous AI agents and multi-agent workflows - Design strict-source-following Retrieval-Augmented Generation (RAG) systems that minimize hallucination and enforce citation integrity - Implement guardrails, structured outputs, and validation layers - Production Engineering - Build scalable backend services using FastAPI - Orchestrate agentic workflows using LangGraph - Deploy and manage AI workloads within AWS or Azure - Optimize model performance, reliability, and cost - Evaluation & Continuous Improvement - Develop rigorous evaluation pipelines measuring: - Accuracy - Citation adherence - Latency - Reliability - Establish metric-driven iteration cycles - Continuously refine deployed systems based on measurable outcomes - Privacy-First Development - Embed privacy-by-design principles across the AI stack - Ensure compliance, data sovereignty, and secure handling practices - Collaborate cross-functionally to align AI capabilities with regulatory standards Qualifications - 5+ years of professional experience - Experience deploying and managing AI workloads in AWS or Azure - Deep technical understanding of LLM usage and orchestration beyond prompt engineering - Strong expertise in Python AI ecosystem, specifically: - FastAPI - LangGraph - Proven experience building: - Complex RAG systems - Autonomous AI agents - Experience building evaluation frameworks and iterating based on performance metrics Requirements - Experience with Knowledge Graphs to enhance RAG precision - Familiarity with Privacy-Enhancing Technologies (PETs) - Experience with data anonymization techniques - Background in compliance-heavy or regulated environments Benefits - Competitive-pay compensation and ownership interest/equity - Unlimited paid time off, plus a requirement to take at least two weeks off per year - We're a Best Place for Working Parents and offer paid parental leave for all new parents - Osano sponsors individual premiums on base plans at 100% and dependent premiums at 50% for Medical, Dental, and Vision insurance via Aetna - A fully and permanently remote company, so you can work from anywhere in the U.S. - Receive a MacBook and $600 to craft your home workspace - Annual company trip designed to foster connection, creativity, and fun - Mental health benefits with free memberships to mindfulness and talk therapy services

• Deploy and configure agentic AI workflows and AI-powered automations within client ServiceNow environments. • Translate customer business requirements into technical architectures and implementation plans. • Implement and integrate NewRocket Agent Packs and AI solutions into enterprise environments. • Work directly with customers to tailor AI solutions to their operational workflows and business processes. • Build demos, prototypes, and proof-of-concept implementations to validate AI-driven workflows with clients. • Rapidly iterate solutions with customers to refine AI-powered use cases. • Support implementation of AI orchestration, LLM integrations, and agentic decision models. • Develop integrations between ServiceNow, enterprise systems, APIs, and AI services. • Build supporting components such as scripts, microservices, automation logic, and integration services. • Implement integrations with AI platforms, APIs, and enterprise data sources. • Actively contribute to the development and evolution of NewRocket’s AI intellectual property and platforms. • Participate in workshops, discovery sessions, and technical working sessions with customers. • Diagnose and resolve technical issues across AI workflows, integrations, and automation pipelines. • Ensure deployed AI solutions are secure, scalable, and production-ready. • Contribute to internal playbooks, reusable deployment patterns, and product evolution.