About the job

About Us

We are a VC-funded, pre-seed startup building the future of agentic commerce. Our platform enables eCommerce brands to deploy intelligent, multimodal AI agents that deliver immersive, high-trust shopping experiences—bridging conversation, product understanding, and real-time decision-making.

As an early team member, you will play a foundational role in shaping the product, the technical architecture, and the company culture. This is an opportunity to build core systems from first principles and define patterns that will scale to millions of users and thousands of merchants.

Role Overview

We are seeking a Senior AI Engineer to lead the design and implementation of the intelligent systems at the core of our product. You will own the AI architecture end-to-end—spanning retrieval-augmented generation (RAG), agentic workflows, real-time voice agents, and multimodal understanding.

This role is for someone who has done this before: an engineer who has already solved hard production problems—low-latency voice interactions, context-aware retrieval, reliable agent orchestration—and can accelerate our trajectory by applying that experience directly.

This is a hands-on technical leadership role. You will work closely with the founders, make architectural decisions, and set the technical direction for our AI systems.

Key ResponsibilitiesOwn the AI Architecture
Design and build the core AI systems, including RAG pipelines, agent orchestration layers, prompt chains, and evaluation frameworks.
Build and Scale Voice AI
Architect low-latency, real-time voice infrastructure capable of natural, context-aware conversations.
Develop Multimodal Intelligence
Build systems for image and video understanding that enable intelligent visual interactions and product comprehension.
Agent & Tool Orchestration
Integrate external tools and services using MCP (Model Context Protocol) and custom orchestration layers to enable reliable agent actions.
Evaluation, Optimization, and Guardrails
Establish evaluation harnesses, implement safety and reliability guardrails, and optimize systems across cost, latency, and quality tradeoffs.
Who You AreYou have built AI systems in production, not just prototypes—and you understand the difference.
You have solved real problems with LLMs: retrieval that actually works, agents that behave predictably, and latency that does not compromise UX.
You have strong architectural opinions informed by experience shipping real products.
You thrive in ambiguity and early-stage environments—you write the playbook rather than follow one.
You want to be the AI expert in the room, with real ownership and influence over technical direction.
You are motivated by impact: shaping the technical DNA of a company, not just shipping incremental features.
Qualifications8+ years of software engineering experience, with 3+ years focused on AI/ML systems in production
Degree in Computer Science, Machine Learning, or a related technical field (or equivalent experience)
Deep hands-on experience with LLM application development, including:
Prompt engineering
RAG architectures
Agent orchestration and tool use
Evaluation and monitoring systems
Production experience with agentic workflows where AI systems take actions, not just generate text
Strong system design instincts, with attention to latency, reliability, cost, and observability
Proficiency in Python
Experience building real-time voice or conversational AI systems
Experience with major LLM providers (OpenAI, Anthropic, Google) and orchestration frameworks (e.g., LangChain or similar)
Experience with training, fine-tuning, or optimizing ML models
Computer vision or multimodal experience (image understanding, visual search, multimodal models)
Familiarity with MCP (Model Context Protocol) or similar tool-use paradigms
Experience with real-time infrastructure (e.g., LiveKit or similar)
Cloud platform experience (GCP preferred)

Nice to Have

Full-stack experience (React / Next.js, TypeScript, NestJS)
Why Join UsGround-floor ownership: Define the AI architecture and technical patterns that will scale with the company.
Meaningful impact: Work directly with founders on core product decisions.
Competitive compensation: Market-competitive salary plus meaningful equity.
Remote-first: Work from anywhere with ~4 hours of overlap with US Pacific time.

Senior AI (Agent) Engineer/ Founding Team