
Member of Technical Staff - AI Memory Engineer
NirvaSan Francisco Bay Area, California, USAOn-Site
Needs a free Superjobs account. You'll finish on Nirva's site.
Skill score
Summary
This person builds the memory system for Nirva's AI companion, covering extraction, consolidation, retrieval, correction, and user control of what is remembered. It suits engineers with hands-on experience building personal or long-term memory and retrieval systems who care about accuracy, provenance, and privacy.
- Function
- Development
- Estimated salary
- Est. $141k–211k/yr
- Estimated for a staff-level role, ~2 yrs experience, United States. Not published by the employer.
- Work mode and location
- On-Site, San Francisco Bay Area, California, USA
- Experience
- 2+ yrs
Job description
Overview
We're hiring an AI Memory Engineer to build how Nirva remembers a person over time: the memory system at the heart of the personal companion.
- Turn messy transcripts, events, and moments into memory that is accurate, updatable, retrievable at the right moment, and controllable by the user.
Roles and responsibilities
- Build the long-term memory system, including episodic memory, semantic memory, and evolving user models.
- Build extraction pipelines that turn transcripts, context, events, and interactions into structured memories with source, confidence, and time attached.
- Own consolidation, summarization, and hierarchy from raw moments into daily summaries, life chapters, people profiles, and durable preferences.
- Own retrieval and context injection so the right memories reach prompts and agent workflows within a context budget.
- Handle updating, correction, conflict resolution, and forgetting so old information can be replaced, contradictions resolved, stale memories decayed or archived, and hallucinated memories never become fact.
- Build for user trust and control so users can see, edit, and delete what Nirva remembers.
- Run memory evals including recall and precision, stale and hallucinated memory rates, and longitudinal consistency.
Skills required
Top skills
- LLMs
- embeddings
- retrieval
- structured outputs
All skills (8)
- summarization
- classification
- context engineering
- knowledge graphs
- entity and relationship models
- memory systems
- evals
- debugging
Qualifications
- 2+ years of full-time engineering experience, or a PhD in computer science, machine learning, NLP, information retrieval, or a related field, plus 2 applied internships where you shipped or evaluated real systems.
- Hands-on experience building a memory system, personal knowledge system, or long-term personalization system, not just a one-shot RAG demo.
- Strong working knowledge of LLMs, embeddings, retrieval, structured outputs, summarization, classification, and context engineering.
- Experience structuring personal data through knowledge graphs, entity and relationship models, timelines, or context stores.
- Strong eval and debugging mindset, and care for accuracy, provenance, confidence, privacy, and user control.
Other details
- Location: San Francisco Bay Area, in person.
- Type: Full-time.
- Pay: $180k–$350k, level dependent, plus meaningful equity.
Company info
About Nirva
Nirva is building the first AI fashion accessory for your mind — a necklace or bracelet that privately listens only to the wearer to enable proactive journaling, emotion tracking, and life coaching. Backed by Lightspeed and South Park Commons, recognized at CES within 90 days of founding, and launching in