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

• Own the end-to-end voice AI architecture — from Twilio media streams through LLM orchestration to TTS output and call disposition. • Design and implement multi-agent systems using tool calling, agent handoffs, and shared conversation state for complex patient workflows. • Build and optimize real-time audio pipelines — WebSocket streaming, codec handling (mulaw/PCM), VAD configuration, and interruption management. • Architect analytics and observability infrastructure for voice-specific metrics: per-segment latency (STT/LLM/TTS), call efficacy, disposition accuracy, and ASR error rates. • Solve voice-specific challenges: turn-taking timing, silence detection thresholds, barge-in recovery, medical term recognition, and end-to-end latency optimization. • Integrate voice agents with internal services via secure authenticated APIs. • Drive platform reliability — eliminate single points of failure, implement multi-provider LLM failover, and design graceful degradation paths. • Collaborate with product and clinical operations to improve self-serve efficacy rates and reduce call escalations. • Mentor team members on voice AI best practices and contribute to architectural decisions.

• Take ownership of assigned voice AI features and components, guiding them through the full software development lifecycle. • Contribute to design discussions, code reviews, and best practice adoption within the Voice AI team. • Drive technical decisions on voice pipeline optimization — VAD tuning, turn-taking, interruption handling, and latency management. • Plan and prioritize tasks in an Agile environment, ensuring timely and high-quality delivery. • Work with Product Managers and stakeholders to refine requirements and scope technical efforts for conversational AI features. • Monitor voice platform health metrics (call efficacy, ASR accuracy, per-segment latency) and prioritize improvements based on data. • Mentor junior team members, sharing knowledge and best practices in voice AI architecture, TypeScript, and real-time systems. • Encourage a culture of continuous learning and technical excellence through pair programming and design reviews. • Document voice AI patterns, integration contracts, and operational runbooks for the team. • Partner with Product Managers, QA, and clinical operations to gather requirements, validate conversational designs, and guide projects from inception to deployment. • Coordinate with other engineering teams to integrate voice agents with internal services via authenticated APIs. • Work with the analytics team to ensure voice metrics flow correctly through the data pipeline for reporting and optimization. • Drive improvements in our multi-agent orchestration approach — tool calling patterns, agent handoff logic, and state management across conversation turns. • Advocate for high-quality standards and automated testing strategies for conversational AI systems, including voice-specific test patterns (simulated calls, transcript validation, latency benchmarks). • Identify and resolve voice-specific UX issues: ASR errors on medical terminology, silence detection tuning, barge-in recovery, and end-to-end response latency.

• 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.