Back to jobs

Member of Technical Staff - AI Memory Engineer

Pay
Pay not listed
Work setting
Not stated
Employment
Full-time — employment source
· Full-time ·
Read the full posting

What you’ll work on

Full posting
  • You will work directly with the founding team to build this system from the ground up.

  • Build user trust and control: users can see what Nirva remembers, edit it, delete it, and understand why it was used

  • Build evals for memory: recall and precision of retrieval, stale and hallucinated memory rates, longitudinal consistency, and failure analysis on real, messy personal data

From the employer’s posting
THE ROLE We’re looking for an AI Memory Engineer to build how Nirva remembers a person over time: the memory system at the heart of our personal companion. Nirva is not a chatbot with a longer context window. It listens to real life, and it has to turn messy transcripts, events, and moments into memory that is accurate, updatable, retrievable at the right moment, and controllable by the user. You will design what gets remembered, how it is structured, summarized, consolidated, corrected, and forgotten, and how it is injected into chat, journaling, recaps, and proactive experiences so the product feels genuinely personal, not generic. You will work directly with the founding team to build this system from the ground up. WHAT YOU'LL OWN
Handle updating, correction, conflict, and forgetting: new information replaces old information, contradictions are resolved, stale memories decay or are archived, and no hallucinated memory becomes “fact” Build user trust and control: users can see what Nirva remembers, edit it, delete it, and understand why it was used Build evals for memory: recall and precision of retrieval, stale and hallucinated memory rates, longitudinal consistency, and failure analysis on real, messy personal data
Build user trust and control: users can see what Nirva remembers, edit it, delete it, and understand why it was used Build evals for memory: recall and precision of retrieval, stale and hallucinated memory rates, longitudinal consistency, and failure analysis on real, messy personal data Partner with product, design, audio, and recommendation teams so memory powers chat, journaling, daily recaps, emotional insights, and proactive experiences
Education & alternatives
Must-haves - 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 (industry or applied research) 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: extraction, storage, retrieval, ranking, and updating over time

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.

In the employer’s words · Read in context

Apply at Nirva

Posting record

Report an error

Actively hiringFirst seen by us 11 days ago, still listed, and not a repost of an earlier posting.

Status in our records
Live
First seen by us
Nov 10, 202611 days ago
Recorded sightings
12
Last seen by us
Nov 21, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Time since we first saw it

Day 11

Similar jobs usually come down between day 1 and day 15.

From 1,368 similar postings that came down. Coming down is not always a hire.

Nirva is hiring

1 open job

Open jobs by the week we first saw them, last 12 weeks.

Hiring record

See how this role fits your experience

Add your resume to compare the role’s scope, tools and requirements with your experience.

Your next step

Complete your application on www.nirva.life. The employer’s form will show what is required.

Already applied? Track this application

Job description

View original posting ↗

← BACK TO CAREERS

Member of Technical Staff - AI Memory Engineer

San Francisco Bay Area

·

Full-time

·

180k-350k

·

level dependent

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. Think Oura Ring for your Mind.

Backed by Lightspeed and South Park Commons, recognized at CES within 90 days of founding, and launching in the U.S. this fall. Co-founders bring backgrounds from Meta Reality Labs (Quest, Ray-Ban glasses) and fashion industry.

THE ROLE

We’re looking for an AI Memory Engineer to build how Nirva remembers a person over time: the memory system at the heart of our personal companion. Nirva is not a chatbot with a longer context window. It listens to real life, and it has to turn messy transcripts, events, and moments into memory that is accurate, updatable, retrievable at the right moment, and controllable by the user. You will design what gets remembered, how it is structured, summarized, consolidated, corrected, and forgotten, and how it is injected into chat, journaling, recaps, and proactive experiences so the product feels genuinely personal, not generic. You will work directly with the founding team to build this system from the ground up.

WHAT YOU'LL OWN

  • Design and build Nirva’s long-term memory system for a personal companion: episodic memory (what happened), semantic memory (facts, people, preferences, relationships), and evolving user models over weeks and months

  • Build extraction pipelines that turn transcripts, user context, events, and interactions into structured, high-quality memories, with source, confidence, and time attached to every memory

  • Build consolidation, summarization, and hierarchy: how raw moments become daily summaries, life chapters, people profiles, and durable preferences without losing the specific detail that makes them feel true

  • Own retrieval and context injection: how Nirva retrieves, ranks, summarizes, and injects the right memories into a prompt or agent workflow, within a context budget, so responses feel specific and grounded

  • Handle updating, correction, conflict, and forgetting: new information replaces old information, contradictions are resolved, stale memories decay or are archived, and no hallucinated memory becomes “fact”

  • Build user trust and control: users can see what Nirva remembers, edit it, delete it, and understand why it was used

  • Build evals for memory: recall and precision of retrieval, stale and hallucinated memory rates, longitudinal consistency, and failure analysis on real, messy personal data

  • Partner with product, design, audio, and recommendation teams so memory powers chat, journaling, daily recaps, emotional insights, and proactive experiences

WHAT WE'RE LOOKING FOR

Must-haves

  • 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 (industry or applied research) 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: extraction, storage, retrieval, ranking, and updating over time

  • Strong working knowledge of LLMs, embeddings, retrieval, structured outputs, summarization, classification, and context engineering, and how each fails in production

  • Experience structuring personal data: knowledge graphs, entity and relationship models, timelines, or context stores

  • Strong eval and debugging mindset for AI systems: you can define what a good memory is, build test cases from real failures, and improve extraction, retrieval, or prompts systematically

  • Care for accuracy and trust in personal data: provenance, confidence, privacy, and user control are part of your design, not an afterthought

  • Strong product engineering instincts and high ownership: you turn model capability into polished, user-facing experiences and drive work to shipped quality

  • Comfortable with ambiguous, subjective, human-centered AI problems, and energized by 0-to-1 work, fast iteration, and early-stage startup intensity

  • Based in San Francisco and able to work in person

Strong signals (nice-to-haves)

  • Built memory for an AI companion, journaling, coaching, wellness, or consumer AI product

  • Experience with long-term user modeling, personal knowledge graphs, or life-logging data

  • Eval frameworks, data flywheels, fine-tuning, or human feedback loops for memory quality

  • Voice / audio context: building memory from transcripts, diarization, or real-world events

  • Experience spanning backend, AI infrastructure, and user-facing surfaces, including mobile

COMPENSATION

San Francisco Bay Area · Full-time · 180k-350k, level dependent

TO APPLY

Apply here

© 2026, nirva labs

go UP

Demand for AI Engineer roles

New AI Engineer postings at the employers we follow are up 340% over the last 6 weeks compared with the 6 before.

Weekly new AI Engineer postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 78, the most 803, and the latest week had 438.
August 17Last week

Each bar is one week of new postings. The darkest bars are the last 6 weeks.

Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.

About the role

We file this job under AI Engineer, by the work the posting describes.

AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.

Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.

An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

San Francisco Bay Area

Working pattern and location restrictions need checking in the full posting.

Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.