Founding AI Engineer

Voice Agent Pipeline Developer

Our client is building the conversational voice layer for how people work. People already use dictation for input and text-to-speech for output. They are going further: a single continuous conversation where users can stay in flow, get responses back, and actually get things done without stepping out of their workflow.

They are initially building for people with vision impairment — a community where this type of interface is not a nice-to-have, but essential. However, this is not a niche product. The same way curb cuts were designed for wheelchair users and ultimately benefited everyone, accessibility is being used as the design constraint to build something meaningfully better.

The long-term vision is a product that scales far beyond accessibility use cases — ultimately serving hundreds of millions of sighted users who want to stay productive while commuting, working away from a screen, or remaining in flow throughout their day.

What You'll Own

The quality of our AI agent is the product. You'll own the intelligence layer, this isn't a research role. This is the person who makes the agent reliable, fast, and smart enough that users trust it with their actual work.

• Voice agent pipeline: Designing and optimizing the full model orchestration chain for real-time, low-latency conversational interactions. You'll decide which models to use, how to stitch them together, and how to make the whole thing feel instant.
• Prompt engineering and evals: Crafting, testing, and iterating on prompts across the product. Building eval frameworks that catch regressions before users do.
• Agentic workflow orchestration: Building multi-step reasoning and action-taking capabilities that let users manage email, calendar, and documents through natural conversation. Handling context management, memory, and deciding when the agent should act versus ask.
• You'll continuously make hard tradeoffs between quality, latency, and cost across the stack.

Requirements

• 2–5 years of experience as a software engineer
• Experience building and shipping AI agents

Location & Work Policy

• On-site in San Francisco
• Full-time role

Tech Stack

• Python
• JavaScript
• TypeScript
• LLM APIs (OpenAI, Anthropic, Mistral, etc.)
• LLM evals
• Applied GenAI tooling

From Tangerine Search:

Tangerine Search is an equal opportunity agency that values diversity. We do not discriminate on the basis of race, religion, color, national origin, sex, gender, gender expression, sexual orientation, age, marital status, veteran status, or disability status. We will ensure that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process, to perform crucial job functions, and to receive other benefits and privileges of employment.