Salary / Hourly Rate: $250,000 - $250,000 per year
Benefits: In-person SF team; high ownership on a 5-person, seed-stage startup.,Meaningful equity; fast path to scope as the product/function owner.,US Citizens Only,Open to Exceptional New Grads
Role Information
Role Overview: N/A
Responsibilities: You will be the force-multiplier who turns research and product ideas into reliable, safe, user-visible features fast. On any given day you'll design prompt/agent workflows, write tooling, build evaluation and safety guardrails, and ship to production alongside the founders — always raising the quality bar for real outcomes., Ship end-to-end full-stack systems: you’ll build the core simulation platform where AI agents execute software engineering workflows (backend in Python, frontend in TypeScript/React)., Design realistic evaluation scenarios and production-grade loops: you’ll define meaningful engineering tasks, establish grading criteria, choose tooling and workflows, and build infrastructure (unit tests, regression suites, shadow/prod checks) that measure reliability and user outcomes., Build and iterate safety-first systems: you’ll implement risk-response detection, guardrails and fallback paths, human-in-the-loop escalation, post-incident reviews, and treat system safety as a first-class product feature., Own critical internal services and tooling: you’ll build lightweight internal tools (UX hooks, service APIs, automation) that speed up experimentation and engineer feedback loops., Collaborate across disciplines: you’ll partner with design (voice/chat UX) and clinical research (for measurement and impact) to translate findings into product improvements and safety safeguards., Drive a high-cadence shipping culture: you’ll move with urgency — prototype, evaluate, harden and release weekly, document decisions and metrics so the team can build confidently and scale fast.
Qualifications: We are optimized for builders: you have shipped real products (internships or full-time) and you love the loop of design → measurement → iteration in a small-team environment., Strong software engineering fundamentals: you’re fluent in Python and you have hands-on experience with full-stack development (TypeScript/React or equivalent). You’ve built tools/features that real users touched, not just prototypes., Product-sense plus speed: you can simplify ambiguous problems into pragmatic baselines, deliver value in days (not quarters), and iterate rapidly while maintaining high standards., Experience with system quality and safety: you have built guardrails (error detection, fallback paths, monitoring), and you are comfortable being accountable for production quality—not just writing code, but delivering sustained value., Evidence-driven mindset: you instrument features, define measurable outcomes (not just engagement), and iterate based on data and feedback loops., Collaboration in high-trust, high-ownership teams: you thrive building in-person with founders and cross-functional partners (design/research). You’re excited to raise questions, shape architecture, and drive new standards., Location & work-auth fit: In-person in San Francisco is required; US work authorization (no sponsorship) is required., Bonus: Prior internship or experience at a top-tier tech or startup, and/or degree from a highly ranked engineering school.
Minimum Requirements: In-person in San Francisco (team works onsite),Must be legally authorized to work in the United States now and for the foreseeable future without employer sponsorship.,Proven track record of shipping software features end-to-end
Screening Questions: (Optional Video). This step is completely optional. If you’d like, record a short 2–3 minute video introducing yourself and your experience — or share a recording of your interview with the recruiter if that’s easier. You can upload the link via Loom or Google Drive. This just helps us get to know you better, but there’s no pressure if you’d prefer to skip it.,(Optional Portfolio / GitHub) If available, please share a link to your GitHub, portfolio, or any recent projects you’ve worked on. This is entirely optional but helps provide more context about your work.,Why this role? What about our mission and our in-person San Francisco team resonates with you?
Company Information
About Company: N/A
Culture: N/A
Additional Information
Interview Process: Step 1: Vibe check call (~15 minutes) A quick introduction to align on mission, confirm in-person San Francisco work suitability, and verify US work-authorization fit. Step 2: Technical take-home (~4 hours, compensated) Candidates build a small full-stack feature or evaluation pipeline relevant to voice + text workflows (e.g., prompt/agent design, tool use/ function-calling, safety checks). Provide notes on trade-offs and what you’d test next. Step 3: Technical deep-dive & code review (~30-45 minutes) Walk through the take-home plus 1–2 shipped or live agent/LLM features. Explore prompts, evaluation loops, latency/turn-taking handling, and how you measured quality and reliability. Step 4: In-person trial in San Francisco (1–2 days, paid) Work onsite with founders on a scoped feature: prototype → evaluate → harden → ship. We assess clarity, speed, product sense, how you reason about safety and measurable outcomes, and your ability to collaborate in-person with our team. Step 5: Offer Fast debrief, reference check if needed, and compensation/equity discussion aligned with our listed range.
Day to day: You will work at the frontier of what software engineering could be, designing, building and shipping the core features of a simulation environment where AI agents execute full-stack engineering workflows. On any given day you’ll write Python and TypeScript/React code, build pipelines, design evaluation loops, and partner with founders to move quickly from prototype to release. You’ll build tools around agent prompting and feedback, add guardrails and observability, and ensure what you ship has measuring real outcomes— not just ticking boxes.
Team: Work directly with the three founders on a ~5-person team in person in San Francisco. You’ll pair with design on voice/chat UX and with research on measurement and risk mitigation, keeping feedback loops tight and decisions pragmatic. (YC lists skills as Prompt Engineering, Python; the culture emphasizes on-site collaboration.)
Growth: As one of the early engineers you’ll not just execute—you’ll help define the standards: architecture for agent workflows, tooling for evaluation and monitoring, and practices for shipping safe, reliable systems. You’ll set the technical direction and have the ability to lead new domains as the company scales. This is more than a job—it’s a career accelerator. You’ll gain ownership, deep technical responsibility, and the chance to grow into a major engineering leader in a next-gen company.
Ideal Candidate Profile: You’ve shipped real software (internship or full-time) and played a substantial role in the lifecycle: discovery → design → implementation → iteration., You’re fluent in back-end engineering (Python) and comfortable across full-stack work in a modern front-end stack (e.g., TypeScript/React)., You’ve worked in production: whether you built tooling, services, UI or infrastructure, you understand trade-offs, can instrument outcomes, and can speak to reliability, performance, and user-impact., You treat safety and quality as features: you’ve designed guardrails, fallback paths, monitoring, or other systems that ensure production code behaves as intended and responsibly., You thrive in a high-ownership, in-person environment: you’re able to collaborate closely with founders and early engineers, raise questions, iterate fast, and help shape how things get built., Bonus: You have experience at a top-tier tech company or startup, or from a competitive engineering program — and you carry a mindset of “I’ll build for the next level, not just the next sprint”., Alex Beal — LinkedIn: linkedin.com/in/beala LinkedIn, Byron Luk — LinkedIn: linkedin.com/in/byron-luk LinkedIn, Polished but unshipped projects with no real end-users or production impact., Candidates unable to commit to in-person work in San Francisco., Little to no experience in safety-oriented systems or conversation/agent-driven workflows.
