Role Description 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 Points 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. Qualifications - Strong experience in Python with AI/ML systems. - Hands-on experience with LLMs (OpenAI API or similar). - Experience deploying AI services with FastAPI. - Familiarity with agentic AI frameworks and orchestration patterns. - Experience working in cloud-based AI environments (Azure preferred). - Solid understanding of data processing, evaluation, and optimization. - Proficiency with Git and collaborative development workflows. Preferred Qualifications - Experience with vector databases (e.g., PGVector). - Familiarity with MLOps practices and AI CI/CD pipelines. - Experience with prompt engineering and evaluation frameworks. - Exposure to multi-tenant SaaS AI systems. Benefits - Flexible work structure of 20–40 hours per week, depending on role scope and workload. - Outcome-driven role, not hour-tracked. - Compensation as a fixed monthly stipend, aligned to responsibilities and expected ownership. - Stipend remains consistent as long as commitments are met and performance remains strong. - Environment requires clear ownership and follow-through, proactive communication, and consistent, high-quality delivery. - Flexibility is paired with accountability—team members are trusted to manage their time while ensuring outcomes, team continuity, and customer commitments are fully upheld.

• Own AI features end-to-end, from problem statement to GA • Move features through our rollout tiers (prototype → design partner → beta → GA), earning each promotion with an eval baseline and a capacity plan • Build and defend evals: golden datasets, a north-star metric per feature, and online monitoring — so we can *see and prove* how a feature behaves, not guess • Lead the "meaning" layer of our semantic stack: retrieval semantics, embedding quality (proven first on initiative-candidate retrieval), and the label flywheel that feeds prompt optimization and golden sets. You co-design our vector and knowledge-graph stores with the AI Platform team — you're their most demanding customer • Push output quality with the levers that matter: context assembly, prompt optimization, and per-customer/per-firm generation • Work closely with cross-functional teams — product managers, designers, and other engineers — to gather requirements, define measures of success, and deliver high-quality solutions • We want you not just to build but to *engage* with our product and our users. Your input and opinion will be highly valuable, and it is expected that you have many thoughts on how things should be done and why

• Implement new product features & support/ extend existing ones • Build frontend platform components leveraged across our internal, external products and ecommerce storefronts like Shopify, Salesforce etc • Work with product and design teams toTranslate product and design work (Figma) into robust, accessible, high-performance UI components • Own frontend architecture decisions and uphold code-quality standards alongside other senior engineers, and mentor teammates through code review • Contribute to development and maintenance of backend services using primarily Golang, Node.js • Understanding of google cloud platform (GCP), CI/CD and be able to deploy code and infrastructure components • Work with datastores like PostgreSQL, Cloud Spanner, BigQuery, and Bigtable • Understand and implement RESTful or GraphQL APIs

• Design, develop, and deploy scalable AI and Generative AI solutions. • Build LLM-powered applications, intelligent assistants, copilots, AI agents, and automated workflows. • Design and implement Retrieval-Augmented Generation (RAG) architectures. • Implement semantic search, embeddings, knowledge retrieval, and vector database solutions. • Integrate Large Language Models through Azure OpenAI, OpenAI APIs, or equivalent AI platforms. • Develop prompts, tools, function-calling workflows, and agent orchestration mechanisms. • Evaluate and select AI models, frameworks, and architectures according to each use case. • Define evaluation criteria and monitor the accuracy, quality, latency, security, and cost of AI solutions. • Integrate AI capabilities into existing software products and enterprise applications. • Transform business requirements into scalable, secure, and production-ready technical solutions. • Provide technical leadership and define development standards and best practices for AI initiatives. • Collaborate with multidisciplinary technical and business teams.