• Own end-to-end development of LLM features: problem framing, data prep, prototyping, offline/online evaluation, deployment, and monitoring. • Build retrieval-augmented generation (RAG) pipelines with vector search (e.g., FAISS, Pinecone, OpenSearch/KNN) and document orchestration. • Implement prompt strategies, tool use/function calling, and guardrails for safety, bias, and privacy. • Integrate models in production services (REST/GraphQL/gRPC), including auth, rate limiting, and observability. • Stand up evals and experiment frameworks (A/B tests, golden sets, regression suites) with clear success metrics. • Optimize for latency, cost, and quality: prompt compression, caching, model selection, fine-tuning/LoRA, distillation where appropriate. • Collaborate with DevOps/MLOps/Platform to automate CI/CD, data/version management, and feature flags. • Embed with CX/Support to mine tickets, chats, and call transcripts; convert VOC into training/eval datasets and backlog priorities. • Instrument user journeys and define online/offline evals (win rate, hallucination rate, TTR, CSAT/NPS); run A/B tests and ship iterative improvements. • Build feedback loops (thumbs-up/down, rationale capture, escalation) and human-in-the-loop fallbacks that protect quality. • Own reliability and UX details that matter for customers: latency budgets, safe fallbacks, clear handoff to human agents, accessibility. • Partner with Trust/Legal/Security to ensure privacy-by-design and compliant data handling; implement guardrails and red-team mitigations.

About the Role We’re hiring a developer with deep, hands-on experience building with MCP and ChatGPT Apps. This is not a general AI role. You should already be comfortable working inside these ecosystems, even if that experience comes from building, testing, or experimenting with your own projects. This is a remote or in-person role (Austin, TX). You’ll be responsible for creating production-grade AI applications, iterating quickly, and pushing the boundaries of what MCP and ChatGPT Apps can do. What You’ll Do - Build, deploy, and maintain MCP-based applications - Develop and optimize ChatGPT Apps using tools, structured outputs, and workflows - Design AI-native product experiences from the ground up - Rapidly prototype and test new ideas using MCP and ChatGPT environments - Use Claude Code as part of your development workflow - Improve performance, reliability, and usability of AI-driven features - Collaborate on product direction and technical architecture What We’re Looking For - Someone who has already spent serious time inside MCP + ChatGPT App environments - Builders who experiment, ship quickly, and learn by doing - Developers who understand both the technical and product side of AI apps - People who can operate with high ownership and minimal oversight

About Our Client Servant is partnering with a forward-thinking organization focused on helping teams work smarter, not harder. By combining thoughtful strategy, intuitive tools, and a people-first mindset, enabling organizations to optimize how work gets done—improving efficiency, clarity, and outcomes across the business. With a strong emphasis on collaboration and continuous improvement, our client partners closely with its customers to solve real-world challenges and deliver practical, scalable solutions. The team values curiosity, ownership, and impact, and is committed to building products and experiences that genuinely support the way people work today. As our client continues to grow, they are investing in talented, mission-driven individuals who want to shape the future of work and make a meaningful difference for customers and teammates alike. Role Summary Our client is building the world’s first Human-Led AI Orchestration Layer—a platform designed to keep humans firmly in control of AI through clarity, accountability, and execution via our proprietary Action Points. As an AI Engineer, you will design and implement the intelligence layer that translates raw information into human-directed outcomes. You will work across LLMs, agentic workflows, and AI pipelines to ensure AI remains a tool governed by human intent, not an autonomous system. Everything you build is expected to be revenue-ready, secure, and production-grade. Key Responsibilities AI & Intelligence Engineering - Design and implement AI-driven workflows that generate actionable, human-directed insights. - Build and optimize LLM-powered systems for summarization, recommendation, classification, and orchestration. - Implement agentic AI patterns that operate under explicit human guardrails and approval flows. - Translate unstructured data into structured Action Points™ aligned with user goals. - Develop and maintain prompt architectures and evaluation frameworks for consistent AI output quality. - Architect and develop semi-autonomous AI agents with mandatory human-in-the-loop control points, safety guardrails, and review checkpoints. Voice to Text - Design and implement AI-driven voice workflows that generate actionable, human-directed insights. - Architect real-time speech-to-text pipelines for AI control, command execution, and Action Point generation. - Implement low-latency voice ingestion using Azure Speech SDK for real-time transcription, intent detection, and multilingual support. - Ensure voice inputs are securely processed, auditable, and aligned with human authorization and approval flows. - Translate spoken input into structured, human-directed Action Point that govern downstream AI agents. Integration & Deployment - Deploy AI services using FastAPI and integrate them securely with backend systems. - Collaborate with frontend and backend engineers to expose AI capabilities via secure APIs. - Ensure AI systems scale reliably in cloud environments (Azure-based). Performance, Ethics & Governance - Optimize inference latency, throughput, and cost efficiency. - Implement observability, logging, and monitoring for AI workflows. - Apply responsible AI principles: transparency, auditability, and human override by design.

Role Description We're looking for a technically curious IT professional who is genuinely excited about AI — not just as a buzzword, but as a day-to-day working tool. This is a hybrid role: part IT engineer, part developer, part AI automation builder. You'll own the administration and reliability of our internal systems while also writing code, building integrations, and shipping agentic workflows that reduce manual work across the organisation. The ideal candidate is either a developer who has moved into IT, or an IT engineer with solid coding skills — someone comfortable context-switching between infrastructure, automation scripting, and hands-on AI tooling. Personal projects and self-taught experience count just as much as formal work history — we care about what you've built and how fast you learn, not just where you worked. You'll be working closely with engineering and operations. If you thrive in async-first, international environments and love being the person who makes everyone else's work easier — this is for you. A Note on Pace: We're an AI-native team, and we expect AI-native output velocity. Tasks that would have taken a week in 2022 should take hours today — and we mean that literally. We use Claude, Cursor, and whatever else gets the job done. We don't measure how long something took; we measure whether it shipped, works, and is maintainable. If you're still working the way you worked two years ago, this role will be frustrating for both of us. If you've already rewired how you work around AI tooling — you'll feel right at home. Key Responsibilities - AI & Automation Engineering - Design, build, and maintain AI-powered internal workflows to reduce manual work across departments — using tools like n8n, Make, or LLM-based agents as appropriate. - Implement and maintain MCP (Model Context Protocol) integrations to connect internal tooling and data sources. - Write and own automation scripts and integrations in Python and/or JavaScript; treat code readability and maintainability as a first-class concern. - Prototype agentic systems that solve real team pain points; iterate based on feedback — fast. - IT Infrastructure & SaaS Stack - Own the administration and optimisation of our core SaaS stack: Google Workspace, Jira, Notion, and related platforms. - Manage identity and access controls, SSO, and RBAC across the organisation. - Maintain system reliability, handle incidents, and support day-to-day IT operations. - Apply security hygiene across the stack — access reviews, offboarding, audit logging, SOC 2-aligned controls. - Delivery & Project Management - Take ownership of workstreams end-to-end: scope, prioritise, deliver, and communicate progress without needing to be chased. - Operate at AI-era velocity — tasks are measured in hours, not weeks; use every tool available to get there. - Document systems, processes, and integrations clearly for async consumption by the wider team. - Engage proactively with stakeholders to understand tooling needs and translate them into structured delivery. Qualifications - Coding ability in Python and/or JavaScript — you can write and maintain automation scripts, read unfamiliar codebases, and ship working integrations. - Solid foundation in IT: systems administration, SaaS management, APIs, identity and access controls. - Hands-on curiosity about AI tools and LLM-based workflows — personal or open-source projects absolutely count. - High ownership mindset: you manage your workstreams, flag blockers early, and don't wait to be chased. - Familiarity with Google Workspace, Jira, Notion, Make, n8n. - Awareness of InfoSec basics: SSO, RBAC, SOC 2 concepts, and general security hygiene. - Available to overlap with US business hours (EST/PST) for key meetings and async communication. - Strong written English — you communicate clearly, document well, and don't wait to be asked. - Comfortable working independently in a remote, async-first environment. Nice to have - Experience with LangChain, CrewAI, Cursor AI, or similar agentic frameworks. - Familiarity with MCP (Model Context Protocol) integrations. - Experience working with Claude and the Anthropic API. - Background in both software development and IT/infrastructure — the blend is a strong differentiator. - Previous remote work in international teams. - Open-source contributions or personal AI/automation projects you can share. Benefits - Work at the intersection of AI and internal product — your tools get used every day by your teammates. - High autonomy and ownership — we care about outcomes, not hours. - Real opportunity to grow into AI engineering: you'll be shipping agentic systems from day one, with a team that will invest in your development. - Collaborative, no-bureaucracy culture with a technically strong, international team. - 20 working days of PTO per year. - US holidays and additional days off.