Company Mission / Why This Matters

Two Dots builds verification and risk infrastructure for housing to help solve the housing crisis.

Housing is too expensive because America created a single family mortgage machine to cut average people into home price inflation fueled by soft bans on new development. That worked for many decades, but when a small single family home costs several million dollars, it stops being an engine of opportunity and becomes a source of the very resentment modern mortgages were originally created to solve.

Housing supply has been restricted so much that people have started fabricating documentation or relying on bypasses and overrides to sign up for a payment they can’t really afford. That conceals the problem instead of solving it.

We believe that public and private policy has to change, and that involves breaking the system that conceals our affordability crisis and leaves people without the disposable income required to live satisfying lives, fueling resentment and political instability that turns problems at home into problems for the world.

The Role

Chat agents are becoming the primary interaction surface of the future. It sounds easy to make a good chatbot, but many systems fail because they misunderstand users, overfit prompts, hide structural problems, or turn complex workflows into brittle demos.

We are looking for a software engineer who can build consumer-facing chat agents that serve as the frontend to complex workflows. This role requires a rare combination of user empathy, strong written English, strong Python ability, and a metrics-driven mentality. You should be comfortable using SQL or BigQuery to understand quality, but also know when to roll up your sleeves and do manual QA rather than treating every product problem like back-propagation.

You are essentially a future version of a UX Engineer, but for conversational natural language experiences instead of buttons and forms.

What You'll Work On

1. Consumer-facing chatbots that serve as the frontend to complex workflows

2. Bridging internal workflow APIs and domain object code with the real-world call patterns of AI agents

3. Making smaller models perform like larger models

4. Designing creative ways to automate product judgment, such as using chatbots to roleplay users instead of relying only on manual QA or fixed test cases

5. Working closely with design and product to balance look and feel, interaction quality, and business objectives

What We're Looking For

You understand context management deeply. You know the difference between a workflow that makes LLM calls and a true agent loop with tool calling. You know how to start with a smart model and move to cheaper, faster ones without relying on prompt hacks, “CRITICAL:” advisories, or endless lists of dos and don’ts.

You understand what belongs in tools and APIs versus what belongs in natural language. Designing that boundary should be a fixation for you.

You also understand what is structural and what is in the domain of tone, framing, or model “dark magic.” You care about the headspace the model is operating in, the quality of the user experience, and whether the product actually works for confused real people.

Despite working on agents, you are not in “Gas Town.” You do not believe every problem requires a meta-harness, and you do not outsource your judgment to chatbots. You know when to escalate to MLEs if a problem likely requires fine-tuning or more advanced methods.

You care deeply about user outcomes. You measure how your experiments are doing, proactively solve quality problems, and have the frustration tolerance required for ambiguous chatbot engineering.

The Team

Henson (CEO) started his career selling FX derivatives to hedge funds at Goldman, then worked at a real estate tech startup for several years leading sales. This enables him to engage with the largest institutional property managers and real estate investors in the country and create value through those relationships.

Max (CTO) started out as a software engineer at Blend, a mortgage application company that went public, and went on to work on the search team at Google. That combination of specific consumer fintech experience and knowledge of how sophisticated ML products succeed in production made big enterprise deals work from day 1.

We met in middle school and created a media website together where people could watch and post their flash games and animations. We learned to code, source talent, and forge partnerships - and had 500 active users. Although a tragic addiction to World of Warcraft interrupted work on the website, we got back together to start Two Dots.

Other team members include: Meta ML alumnus with decades of experience, a 21 year old UMich grad who was a top 2,000 LoL player (he is no longer playing the game, thank god), and a former agave farmer who started a shipping and logistics company while at Stanford.

Technical Fit

Python is preferred. TypeScript or other strong software engineering backgrounds are also welcome.

You should be a strong enough programmer to build reliable systems manually, not just prompt your way through implementation.

Compensation

The higher end of the band is for rare candidates with a combination of strong engineering, product judgment, and conversational design experience. The lower end is for solid mid-career software engineers with meaningful professional or personal experience building chat agents that interact with real systems.

About the Interviews

1. Prompt Engineering / Agent Design Screen: We discuss how you approach agent quality, context management, tool use, prompt structure, and evaluation.

2. Behavioral Interview: We ask structured questions about ownership, startup fit, user empathy, ambiguity, and past examples of taking responsibility for quality.

3. Product / Design Interview: We evaluate how you diagnose and improve conversational product experiences, including user-facing language, subjective quality, and measurement.

4. Technical Interview: We assess core software engineering ability, including writing code manually and reasoning through systems without relying on AI coding tools.