Staff Software Engineer, AI

Stord is The Consumer Experience Company, powering seamless checkout through delivery for today's leading brands. They are seeking a Staff Software Engineer to serve as the technical lead of the AI Platform team, responsible for owning architecture decisions, driving technical strategy, and mentoring engineers while working hands-on in their TypeScript-based AI platform.

Responsibilities:

• Own the technical vision and architecture of Stord's AI platform, making decisive design choices and communicating the "why" to stakeholders at all levels
• Drive technical strategy in partnership with the Sr Engineering Manager and Sr Product Manager, translating product goals into sound engineering plans
• Evaluate build-vs-buy decisions, new tools, and architectural patterns with a pragmatic, production-first mindset
• Establish and enforce technical quality standards through design reviews, code reviews, and architectural guidance
• Show up — be present and accountable in critical ceremonies including design reviews, go/no-go releases, sprint planning, and cross-team syncs
• Design and build core components of our AI platform: agent orchestration, tool systems, prompt management, and integration APIs
• Work daily in our TypeScript stack: Hono on Cloudflare Workers, Durable Objects for stateful agents, D1/Drizzle for persistence, and the AI SDK (Anthropic Claude) for model interaction
• Build robust, scope-aware tool systems that safely expose platform capabilities (orders, inventory, knowledge base) to AI agents
• Design fault-tolerant integrations with downstream services, including Elixir/Phoenix APIs, and ensure graceful degradation
• Integrate ML model outputs via API layers as the team's needs evolve, without requiring deep data science expertise
• Be the engineer other engineers go to — cultivate trust and influence with senior and mid-level engineers through consistent technical excellence and availability
• Mentor engineers at all levels, with particular emphasis on growing senior engineers into more autonomous technical decision-makers
• Model and teach directed agentic development practices: how to use AI coding tools effectively, maintain a strong independent technical POV, and produce high-quality results rather than accepting raw model output uncritically
• Create leverage through reusable abstractions, clear documentation of architectural decisions, and developer tooling that makes the rest of the team faster
• Proactively identify technical risks and opportunities — don't wait to be assigned a ticket
• Partner with Product Management to shape the AI product roadmap, providing technical perspective on feasibility, sequencing, and trade-offs
• Work with the Group Principal Engineer to align AI platform architecture with broader engineering strategy
• Collaborate with Data Scientists and ML Engineers to understand model requirements and design clean integration boundaries
• Support other product engineering teams in adopting AI capabilities within their domains

Requirements:

• TypeScript (3+ years in production) — You write idiomatic, well-structured TypeScript and are comfortable owning a large TypeScript codebase. This is the primary language of the AI platform
• Distributed Systems & Edge Computing — Experience designing stateful systems at the edge. Cloudflare Workers, Durable Objects, or similar edge runtime experience is strongly preferred
• AI/LLM Application Development — You have built and shipped agentic or LLM-powered features in production. You understand prompt engineering, tool/function calling, context management, and the practical challenges of making AI systems reliable
• Data Streaming Platforms — Experience consuming from or integrating with event streaming systems (Redpanda preferred, Kafka acceptable). Familiarity with Redpanda Connect or Kafka Connect for building data pipelines that feed AI features is a plus
• API Design & Integration — Experience designing and consuming RESTful APIs, OpenAPI specifications, and event-driven architectures. You'll integrate with multiple backend services daily
• Database & Persistence — Strong SQL fundamentals. Experience with embedded/edge databases (D1, SQLite) or PostgreSQL. Drizzle ORM experience is a plus
• Cloud Platforms — Hands-on experience with Cloudflare, GCP, or AWS. Understanding of serverless and edge deployment models
• Observability — Experience instrumenting production systems with OpenTelemetry, Datadog, or similar. You know what to measure and how to debug distributed systems in production
• Technical Authority — You form well-reasoned technical opinions based on experience and analysis, and you can defend them in a room of strong engineers. You don't outsource your judgment to an LLM
• Force Multiplier Mindset — You measure your impact by team output, not personal ticket velocity. You actively seek opportunities to unblock, teach, and elevate others
• Accountability & Presence — You show up for the team. You're in the design reviews, the release meetings, the architecture discussions. You own outcomes, not just code
• Communication & Influence — You can explain complex technical decisions to PMs, executives, and junior engineers alike. You build consensus through clarity, not authority
• Directed AI-Assisted Development — You know how to use AI coding tools as a force multiplier while maintaining quality. More importantly, you can teach a team to do the same — establishing practices that produce better results than unguided AI output
• Elixir/Phoenix experience or familiarity (downstream services use Elixir)
• Experience with the Cloudflare developer platform (Workers, Durable Objects, Sandboxes, Containers, D1, R2, Vectorize, AI Gateway, Workflows, Queues)
• Experience with Anthropic Claude, the AI SDK (ai / @ai-sdk/anthropic), or Model Context Protocol (MCP)
• Knowledge of logistics, e-commerce, or supply chain domains
• Contributions to open-source TypeScript or AI projects
• Experience with WebSocket-based real-time systems
• Familiarity with scope-based authorization and multi-tenant systems