Profile cover
H

AI Dialogue State Tracking Engineer

Mevra Labs

Remote · $200k+ / 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

Multi-turn conversations are where every chatbot falls apart. The user says "Book me a flight to Paris next Tuesday," then "Actually, make it Wednesday," then "And add a hotel near the Eiffel Tower." Three turns in, the system needs to track flight destination (Paris), departure date (updated to Wednesday), and a new hotel request with location constraint — all without losing context or confusing slots from different intents. Our dialogue state tracker maintains a structured representation of the conversation that evolves with each user turn. It handles slot corrections, multi-intent turns, implicit references ("the same hotel chain as last time"), and context carryover across topic switches. You'll advance the state tracking architecture, pushing accuracy from 89% joint goal accuracy to 95%+ on our benchmark. The conversational AI team is seven engineers. You'll be the senior researcher-engineer who defines the state tracking architecture, designs the evaluation methodology, and bridges the gap between published dialogue research and production deployment. We publish results and encourage conference contributions.

Fully remote.

Responsibilities

  • Advance dialogue state tracking architecture toward 95%+ joint goal accuracy
  • Handle complex phenomena: slot corrections, multi-intent, implicit references
  • Design comprehensive evaluation benchmarks for state tracking quality
  • Build production-grade state tracking serving with sub-100ms latency
  • Publish research findings at NLP conferences
  • Mentor junior engineers on dialogue systems methodology

Requirements

  • 6+ years in NLP with focus on dialogue systems or conversational AI
  • Deep understanding of dialogue state tracking architectures and benchmarks
  • Strong PyTorch and Hugging Face skills for model development
  • Experience deploying dialogue models in production
  • Publications in dialogue systems or related NLP areas preferred

Benefits

  • Fully remote with async-first culture
  • $200K+ total compensation
  • Comprehensive health coverage
  • Unlimited conference travel budget
  • 20% time for independent research

Keep exploring related roles

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

Categories

NLP & Prompt Engineering AI & Machine Learning Engineers

Skills

python pytorch hugging face langchain docker

Related remote AI jobs

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

Browse all jobs

Senior Test Automation Engineer

Rad AI

Full-time Senior

Senior Site Reliability Engineer - (Canada-Remote)

ClickHouse

Full-time Senior

Senior Site Reliability Engineer - (US-Remote)

ClickHouse

Full-time Senior

AI engineer (UK)

Writer

Full-time

AI engineer

Writer

Full-time

AI research scientist

Writer

Full-time

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$200k+ / year

AI Expertise

NLP & Prompt Engineering AI & Machine Learning Engineers

Skills

python pytorch hugging face langchain docker sql

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