Backend Engineer, AI Systems & Memory Orchestration

TwinMind AI, Inc.; Menlo Park (CA); Hybrid; USD 150.000 - 230.000; Vollzeit

Benefits dieser Stelle

Unlimited PTO

Health Insurance

Zusammenfassung

TwinMind AI, Inc. in California is seeking a backend software engineer to help build scalable APIs and machine learning tooling that power a memory-augmented AI assistant.

You will design and ship APIs, data pipelines, and services for memory retrieval and LLM orchestration, while partnering with mobile and product teams to deliver end-to-end features in a fast-moving startup environment.

Qualifikationen

• 4+ years of backend software engineering experience (Python, Go, Java, or similar).
• Hands-on experience with LLMs and agentic workflows through industry work or projects.
• Strong understanding of evaluation methodologies and metrics for generative AI systems.
• Ability to write clear prompt specs or system design docs for engineers and stakeholders.

Aufgaben

• Agentic Workflows: Build the orchestration layer that lets TwinMind decide what it needs, fetch it, and weave it into a natural response within latency budgets.
• Evaluation: Build and maintain evaluation suites that measure response quality, memory retrieval accuracy, and persona consistency.
• Backend Systems: Design and ship APIs, data pipelines, and services powering memory retrieval, context assembly, and LLM orchestration.
• Infrastructure: Own internal frameworks for prompt versioning, A/B testing, and deployment so the team can iterate on AI behavior with confidence.
• Cross-functional Collaboration: Partner with iOS, Android, and product teams to ship new features end-to-end.

Kenntnisse

Backend software engineering

API design

LLMs experience

Prompting / system design

Jobbeschreibung

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

Agentic Workflows: Build the orchestration layer that lets TwinMind decide what it needs (memory lookup, calendar check, web search, or nothing), fetch it, and weave it into a natural response, all within the latency budget of a live conversation.

Evaluation: Build and maintain evaluation suites that measure response quality, memory retrieval accuracy, and persona consistency across rapid product updates.

Backend Systems: Design and ship the APIs, data pipelines, and services that power memory retrieval, context assembly, and LLM orchestration.

Infrastructure: Own the internal frameworks for prompt versioning, A/B testing, and deployment so the team can iterate on AI behavior with confidence.

Cross-functional Collaboration: Partner with iOS, Android, and product teams to ship new features end-to-end, from proactive suggestions to new memory integrations.

Required Qualifications

4+ years of backend software engineering experience (Python, Go, Java, or similar), including designing APIs, working with databases, and building services that run in production.

Demonstrated hands-on experience with LLMs, and agentic workflows (tool use, routing, context management) through industry work, research, or significant personal projects.

Strong understanding of evaluation methodologies and metrics for generative AI systems.

Can write a clear prompt spec or system design doc that both engineers and non-technical stakeholders can follow.

Preferred Qualifications

Deep experience with Retrieval-Augmented Generation (RAG) and managing long-term memory systems for AI.

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…

Love the craft of making language models behave and can find creative ways to make them contextually aware.

Want to be at the intersection of AI capability and product experience, not just one side.

Are comfortable with ambiguity and can independently define success metrics for novel AI features.

Can manage multiple concurrent projects and prioritize ruthlessly in an unstructured, fast-moving environment.

Have a strong founder's mentality: you take extreme ownership and drive projects from conception to production.

Are passionate about building AI systems that are genuinely helpful and seamlessly integrated into users' daily lives.

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.