Infinity Constellation

• You'll lead complex, 0-to-1 engagements: taking ambiguous goals from mid-market leadership teams and turning them into working data systems and measurable business outcomes. • You'll move between executive stakeholders and engineering teams, own the client relationship end-to-end, and help build the internal playbooks that make Paradox scalable. • You'll be the primary partner to clients — leading discovery, aligning stakeholders, defining scope, and staying accountable through launch and adoption. • You'll take whiteboard conversations with clients and turn them into clear specs for engineers — ETL pipelines, semantic models, metric definitions, evaluation criteria. • You'll stay close through prioritization, testing, and rollout. • As a founding team member, you'll help identify what's working across engagements and turn it into repeatable assets — delivery templates, data models, internal tools. You'll contribute to proposals, shape solution approaches for prospective clients, and help Paradox get better at what it does with every project.

• Work across disciplines and collaborate across systems, tools, and functions • Use AI and automation to improve workflows and jumpstart projects • Manage inboxes, draft messages, and communicate clearly • Own shifting calendars, managing time and priorities • Coordinate meetings, travel, and logistics for principals • Track key initiatives and stay ahead of deadlines • Spot workflow friction and implement better systems for efficiency • Manage financial admin tasks with accuracy and discretion

• Own the health, reliability, and evolution of Labrynth's platform across backend, infrastructure, and AI systems • Make architectural and technology decisions, evaluate tradeoffs, choose tools, and stand behind the choices • Support the engineering team by reviewing code, mentoring, unblocking, and setting standards • Tackle complex, ambiguous problems that don't have an obvious solution and drive them to resolution • Build and deploy production services on Cloud (GCP, AWS) • Design and maintain APIs that serve both internal systems and client-facing products • Collaborate directly with clients to understand their problems and translate them into scalable technical solutions • Improve CI/CD pipelines, observability, and developer experience across the team

• Design and own the technical architecture of The SOURCE® • Translate creative, brand, and agency workflows into scalable systems • Build a platform that supports services today and SaaS tomorrow • Make pragmatic decisions about build vs buy vs automate • Ship fast, iterate often, and prioritize leverage over perfection • Build internal tools that reduce scope creep and operational drag • Integrate AI, automation, and workflow tooling where it actually adds value • Establish technical standards, documentation, and patterns early • Act as a thought partner to the founder on product vision and sequencing • Help define what Radiance *should* and *should not* build • Lay the groundwork for future engineering hires and contributors • Own outcomes, not just code

• Build production software with code and Supernal's proprietary platform, including backend services, data models, and CRUD applications • Build and maintain integrations with external systems (APIs, webhooks, third-party tools, and data sources) that AI Employees can safely act on • Design, implement, and deploy conversational agents, including multi-turn flows, state management, and tool usage • Own end-to-end technical delivery for high-priority customer implementations, from architecture through production launch • Translate customer requirements and SOWs into clear technical designs, execution plans, and deliverables • Make and own architectural decisions across application design, API integrations, LLM orchestration, RAG design, and workflow decomposition • Handle real-world voice system challenges including latency, interruptions, fallbacks, error handling, and failure recovery • Write automated tests — unit tests for isolated logic and end-to-end tests for full system and user journey validation • Apply solid error handling: distinguish retryable vs. fatal failures, surface meaningful error messages, and avoid silent failures • Actively debug complex production issues across agent logic, prompts, integrations, and external dependencies • Partner with delivery and product leadership to manage timelines, scope, and technical tradeoffs during implementation • Review technical work for quality, scalability, and maintainability, setting a high bar for engineering excellence • Define, document, and evolve best practices for building and delivering reliable AI Employees

• Lead design execution across brand, web, decks, social, and paid media • Build and maintain scalable brand systems, style guides, and component libraries in Figma • Translate creative direction and strategy into polished, production-ready assets • Support web design with wireframes and layouts (Webflow build skills a plus, not required) • Create internal Radiance marketing assets including case studies, decks, and visual narratives • Ensure consistency, quality, and organization of assets within The Source® • Participate in critiques, concept development, and collaborative reviews • Balance speed and craft—shipping excellent work without over-polish

• Lead design execution across brand, web, decks, social, and paid media • Build and maintain scalable brand systems, style guides, and component libraries in Figma • Translate creative direction and strategy into polished, production-ready assets • Support web design with wireframes and layouts (Webflow build skills a plus, not required) • Create internal Radiance marketing assets including case studies, decks, and visual narratives • Ensure consistency, quality, and organization of assets within The Source® • Participate in critiques, concept development, and collaborative reviews • Balance speed and craft—shipping excellent work without over-polish

• Design and build backend and platform features (APIs, services, integrations, and data flows) • Own scoped projects end-to-end: requirements clarification, implementation, testing, rollout, and follow-through • Write automated tests — unit tests for isolated logic and integration tests for system behavior • Apply solid engineering fundamentals: error handling, retries/backoff where appropriate, and clear interfaces between components • Debug production issues using logs/metrics/traces; drive issues to resolution and add safeguards to prevent recurrence • Improve reliability and maintainability through refactors, performance improvements, and better observability • Communicate progress, tradeoffs, and risks clearly to engineering and cross-functional partners • Contribute to team standards: code review, documentation, and best practices that keep builds predictable and supportable

• Build and extend multi-agent AI pipelines for regulatory document analysis, gap identification, and pre-draft generation • Work with export-controlled materials in a compliant environment • Develop and improve GraphRAG-based knowledge retrieval systems using Neo4j • Integrate and orchestrate LLM calls for document processing workflows • Collaborate with engineers and directly with clients to understand domain requirements and translate them into technical solutions • Contribute to platform architecture as we modularize and scale our systems across multiple regulatory domains

• Ship user-facing agent experiences end-to-end: prototype → production → iteration based on real usage. • Architect and implement stateful agent systems (workflows, tool calling, memory, retrieval, and human-in-the-loop where needed). • Build voice features end-to-end where they unlock value: realtime speech agents, voice UI/UX, prompt/audio routing, and guardrails for safe tool execution. • Build/own an evaluation harness: - curated test sets + scenario suites - automated scoring / rubric-based graders - prompt/model/version tracking - canary + A/B experimentation and safe rollout patterns • Design data + retrieval pipelines: - chunking, enrichment, metadata strategy - hybrid retrieval (vector + keyword + structured filters) - re-ranking, caching, and latency optimization - multi-tenant safety and data isolation • Integrate with and extend our platform primitives: - Django/DRF/ASGI services - async execution + queues + workflow orchestration - PostgreSQL + pgvector - Kubernetes deployments, autoscaling, and cost controls • Establish engineering rigor for agents: - observability (traces, spans, structured logs) - reliability patterns (timeouts, retries, circuit breakers, graceful degradation) - security/privacy controls for data access and tool execution