Applied AI Engineer ( Remote - North American Timezones)

Location: Boulder CO, NYC, or Remote (North America)

Type: Full-Time

Stage: Seed-stage, high-growth startup

Comp: Salary ($125k-200k) + equity + benifits

Company: Mostest

Help build the AI operating system for events.

We’re building the future of events: software that helps people plan extraordinary events, instantly source and book perfect vendors, and execute flawlessly with AI weaving the experience.

We recently raised our seed round and are growing quickly. This role, Applied AI Engineering, is a core function of the company, not a bolt-on specialty. We’re looking for an exceptional Applied AI Engineer to help architect and build intelligent systems at the heart of the product, laying the foundation for a continuously improving system.

This is a role for someone who likes shipping fast, thinking in systems, and turning emerging AI capabilities into durable product advantages.

What you’ll do

You’ll work across product, infrastructure, and AI systems to build core experiences that power vendor discovery, planning/booking workflows, matching, recommendations, and automation.

You’ll design and ship:

• LLM-powered product workflows using retrieval, structured outputs, tools/function calling, and orchestration

• Search, matching, and recommendation systems across large vendor and event datasets

• Multi-step backend pipelines for ingestion, enrichment, ranking, and workflow automation

• Production-grade product features through to full-stack Next.js Applications.

• Multi-tenant permissions systems (RBAC, scoped access, authorization patterns)

• Observability and evaluation systems for AI reliability, quality, and cost balancing

• Internal engineering patterns for compounding engineer that make AI-assisted development faster and safer

Must Have

Applied AI workflow experience

You’ve designed and shipped LLM-backed systems in production, such as:

• Agents or assistents (conversational)

• RAG / retrieval systems

• Tool or function calling

• Eval harnesses

• Reliability patterns

Data + platform expertise

Strong hands-on experience with:

• Postgres schema design and performance tuning

• Supabase (Auth, RLS, migrations)

• Search and retrieval systems

• Embeddings, ranking, chunking, hybrid retrieval

• Workflow orchestration, queues, idempotent jobs, async processing

• Background services on platforms like Render

Systems judgment

Strong instincts around where rigor matters:

• Auth and permissions

• Cost balancing

• Data integrity

• Testing and CI

• Observability and instrumentation

• Reliability, security, and operational discipline

AI-native engineering practice

You actively use tools like Claude Code, Cursor, Codex, Gemini, or equivalent to accelerate delivery without sacrificing quality.

Nice to Have

Bonus points if you have experience with:

• AI chat interfaces and agentic UX

• LLM evals and regression testing

• Security/privacy patterns for AI systems

• Data ingestion and entity resolution pipelines

• Building “compounding engineering” systems that make teams faster over time

Extra: Full-stack engineering depth

This is a small team, so being able to step into other aspects of the stack to unblock tasks and enable velocity is a big add. We value experience delivering production systems end-to-end using:

• TypeScript

• React

• Next.js (App Router preferred)

• Modern API and server-side application patterns

What We’re Looking For

Within this role, success looks like building:

• Fast, accurate vendor discovery and matching workflows

• Reliable AI-powered planning experiences users trust

• Maintainable systems where quality scales with speed

• Reusable engineering patterns that compound over time

• A codebase where AI-assisted development increases leverage without increasing chaos

Our type of people

You might be a fit if you:

• Are excited about tight knit collaboration in small teams

• Curiosity driven, actively learning and adapting

• Fueled about technology that brings people together IRL

• Self driven and prize their autonomy

• Care about elegant systems and product craft equally in an AI era

• Can move quickly without being careless, balancing speed with risk

• Enjoy pairing deep engineering with practical AI experimentation

• Want ownership over foundational architecture, not just implementation

Compensation & Benefits

• Salary + Equity based on experience for a salary range: $125 - 200k

• Flexible, outcomes-first work (remote-friendly across North America)

• health and dental coverage

• Unlimited PTO with an emphasis on sustainable pace

Why Mostest

We build for real-world moments: the show must go on. We’re obsessed with creating the same delight that our events bring with a focus on quality craft, attention to detail, and building for joy. Like our hospitality partners, we rely on trust and integrity: transparent, respectful, and aligned with planners, vendors, and customers. We believe care is infrastructure: flexible, outcomes-first work that supports real lives so we can do our best work for the long haul. If this culture aligns with you, we’d be thrilled to have you join!

Why join now

• Seed-stage company with real traction and ambitious scope

• Opportunity to help define our AI architecture from the ground up

• Work on meaningful product problems, not demo ware

• Small team, high ownership, fast decisions

• Help build what we believe will be a category-defining company

To apply

Send us:

• GitHub / portfolio / LinkedIn

• A few products or systems you’ve shipped and what you specifically built

• (Optional, but encouraged) examples of applied AI workflows, retrieval systems, or agentic products you’ve worked on

We care far more about demonstrated systems thinking and shipped work than keyword matching.