Product Engineer (Mid Level to Senior)

Teal HQ•Miami, FL

2d•Remote

About The Position

Teal is building the next generation of career infrastructure, evolving from a job-search tool to an AI that runs your career. We are developing agents that can scout opportunities, prepare users for interviews, negotiate offers, and maintain a comprehensive career memory. This role involves joining a small, senior engineering team focused on rebuilding the core experience around AI agents. You will ship features directly to millions of users and work on unsolved problems in contextual intelligence, reasoning over messy data, and creating a compounding career memory. The focus is on the new AI-native product, leveraging Teal's existing foundation and user base.

Requirements

Shipped real LLM features in production, including tool use, RAG, and agents that do not silently fail.
Experience with multi-step agents and a strong understanding of effective orchestration patterns.
Full-stack capabilities with proficiency in at least one of React/TypeScript or Rails, and comfort in both.
Willingness to work across the full stack without waiting for hand-offs.
Experience with or strong opinions on AI evaluation systems (harnesses, regression suites, latency/cost budgets).
Proficiency in using AI tools such as Claude Code, Cursor, Codex, and OpenCode.
Demonstrated craft, caring about UX, speed, and polish.
Bias for closure; ability to take a fuzzy problem and deliver a working solution.
Desire for customer proximity, including talking to users, reading tickets, and participating in sales calls.
US-based.
No sponsorship available.

Nice To Haves

Production experience with vector databases.
Experience with MCP servers.
Experience with eval frameworks like Braintrust, Langfuse, or homegrown solutions.
Experience in careers, HR, or recruiting products.

Responsibilities

Ship AI features end-to-end, owning the API, model orchestration, streaming UI, evals, and rollout.
Develop agentic workflows, including multi-step agents for role research, career analysis, bullet writing, interview preparation, and offer negotiation.
Build streaming interfaces that are responsive, handle retries gracefully, and degrade well.
Develop the evaluation system for AI features, including harnesses, regression suites, and latency/cost budgets.
Iterate on prompts and features using A/B testing infrastructure.
Engage with users through customer calls, support tickets, and user interviews.
Build edge-first AI infrastructure on Cloudflare Workers, Durable Objects, AI Gateway, Vectorize, Queues, and R2.
Implement multi-model agent orchestration supporting various AI providers and tool calling.
Develop the interface layer using React, TypeScript, shadcn/ui, and Tailwind, focusing on streaming and responsiveness.
Build and maintain the career memory (vault) using Postgres, pgvector, and semantic recall.
Contribute to the 'boring parts' of the stack, such as Rails and Postgres, ensuring stability.
Shape architectural decisions for agent state, retrieval, model orchestration, and evals.