Fulltime / Internship
About the job
We’re on a mission to make every human superintelligent. Our first product is a personalized "second brain" an AI twin powered by everything you see and hear, that learns with you, remembers your entire life, and helps proactively before you even ask.
Our co-founders are AI scientists who have built moonshots at Google X, deployed production systems with over $1 billion revenue impact on Wall Street, and contributed to a Nobel Prize-winning discovery.
We have raised funding from some of Silicon Valley’s most influential venture capitalists, including the earliest investors in Facebook, Robinhood, and Zapier.
We are seeking brilliant, ambitious minds who are passionate about pushing the limits of AI to make a dent in the universe.
Key Responsibilities
Prompt Engineering Excellence: Design, test, and relentlessly optimize system and feature-specific prompts that shape TwinMind’s behavior, ensuring our assistant remains proactive, warm, and hyper-relevant in real-time audio and text conversations.
Context & Tool Mastery: Build reliable agentic workflows that allow the AI to seamlessly decide when to query a user's past memories, check their calendar, or search the web based on live conversational context.
Evaluation Development: Build and maintain comprehensive evaluation suites (evals) that ensure response quality, memory retrieval accuracy, and persona consistency across rapid product updates.
Cross-functional Collaboration: Partner closely with iOS, Android, Backend and product teams to ensure new features (like proactive push suggestions or new memory integrations) meet our high quality and safety standards.
Rapid Iteration: Work in a highly agile startup environment where underlying model capabilities advance daily, requiring quick adaptation and creative problem-solving to maintain our competitive edge.
Infrastructure Contribution: Help build and refine the internal frameworks that allow our team to develop, A/B test, and deploy prompts with absolute confidence.
Required Qualifications
3+ years of software engineering experience (Python, TypeScript, or similar languages).
Demonstrated hands-on experience with LLMs, complex prompt engineering, and agentic workflows (through industry work, research, or significant personal projects).
Strong understanding of evaluation methodologies, LLM-as-a-judge frameworks, and metrics for generative AI systems.
Excellent written and verbal communication skills—you’ll need to explain complex model behaviors and prompt logic to diverse stakeholders.
Ability to manage multiple concurrent projects, prioritize ruthlessly, and thrive in an unstructured, high-growth startup environment.
Experience with version control, CI/CD, and modern software development practices.
Preferred Qualifications
Deep experience with Retrieval-Augmented Generation (RAG) and managing complex, long-term memory systems for AI.
Experience building and optimizing AI features for mobile (specifically iOS) applications.
Background in Machine Learning, NLP, or related fields.
Experience with A/B testing and experimentation frameworks in a production environment.
Track record of improving AI system performance and latency through systematic evaluation and iteration.
You Might Thrive in This Role If You…
Get incredibly excited about the nuances of how language models behave and love finding creative ways to make them feel more "human" and contextually aware.
Enjoy being at the intersection of AI research and product, translating cutting-edge capabilities into magical user experiences.
Are comfortable with ambiguity and can independently define success metrics for novel, real-time AI features.
Have a strong founder's mentality—you take extreme ownership and drive projects from raw conception to production.
Are passionate about building AI systems that are genuinely helpful, empathetic, and seamlessly integrated into users' daily lives.
Ready to Build the Future?
Location: Menlo Park, California
Benefits: Unlimited PTO, Health Insurance
We encourage you to apply even if you do not believe you meet every single qualification. We are building a deeply empathetic product, and we believe that having a diverse range of perspectives on our team is essential to getting it right.
