Profile cover
H

AI Conversational Memory Management Developer

Mevra Labs

Remote · $60k – $80k / year · Full-time · Posted 5 months ago

No longer accepting applications

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Conversational AI systems have a memory problem: they forget everything when the context window fills up. A customer who explained their situation 10 turns ago shouldn't have to repeat themselves. Our memory management system maintains long-term conversation context beyond token limits using selective compression, hierarchical summarization, and semantic retrieval of relevant past exchanges. You'll build the memory infrastructure: the compression pipeline that distills old conversation turns into compact summaries, the retrieval system that fetches relevant past context for each new turn, and the injection pipeline that seamlessly inserts retrieved memory into the current context without the user noticing the seam. It sounds simple; making it work without context artifacts or inconsistencies is genuinely hard. The conversational platform team is five engineers. You'll start with the compression module, learning how conversation content loses information as it's summarized. Your senior teammate designs the retrieval architecture; you'll build the compression that makes retrieved memories compact enough to inject without consuming the full context budget.

Fully remote.

Responsibilities

  • Build conversation compression reducing old turns to compact summaries
  • Implement semantic retrieval fetching relevant past exchanges
  • Design seamless context injection without visible seams
  • Handle compression trade-offs between fidelity and token efficiency
  • Test memory accuracy across multi-session conversations
  • Monitor memory consistency and identify compression failure patterns

Requirements

  • 1+ year of Python development experience
  • Basic understanding of LLMs, tokenization, and context window concepts
  • Familiarity with LangChain or similar orchestration frameworks
  • Interest in conversational AI and natural language processing
  • Systematic approach to testing edge cases in text processing

Benefits

  • Fully remote with flexible schedule
  • Health and dental insurance
  • $1,500 learning stipend
  • Mentorship from senior NLP engineers
  • Work on a core challenge in production conversational AI

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

NLP & Prompt Engineering MLOps & AI Infrastructure

Skills

python langchain sql fastapi docker

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Technical Support Engineer - APAC

Hyperbolic

Contract

Senior Engineer, Exposure & Vulnerability Management

Recursion

Full-time Senior

Software Engineer

Turing

Full-time

Principal AI Security Engineer

Cerebras

Full-time Principal

Senior Solution Engineer, Partnerships - Brazil

Snowflake

Full-time Senior

Senior Product Analyst / Data Scientist

Nebius

Full-time Senior

Job Type

Full-time

Level

Junior

Language

English

Salary Range

$60k – $80k / year

AI Expertise

NLP & Prompt Engineering MLOps & AI Infrastructure

Skills

python langchain sql fastapi docker aws

Ready to apply for this role?

Create a free talent account.

  • Find AI roles in one place
  • Get AI-matched job recommendations
  • Reply to companies that message you
  • Build your public AI talent profile
Create free profile and apply Log in

This role is closed. Create your free profile to apply to similar open roles.

Don't miss the next one: get matched to new roles like this.

Create free profile