Senior Software Engineer, Voice AI (Speaker Recognition & Transcription)

TLDX SOLUTIONS GMBHSão Paulostepstoneavaldatud 19.11.2026
Nõutav:TypeScriptPythonNode.jsDevOpsQA/TestAISecuritySeniorRemote

Context

tl;dv helps revenue, customer, product and leadership teams turn meetings into structured intelligence. We record, transcribe, summarise and analyze meetings, so teams understand what’s happening across sales demos, feedback calls, onboarding sessions and internal discussions.

We’re growing fast: revenue is up 5x and usage 10x over the last 12 months. Everything we do starts with two questions: what was said, and who said it. Transcription and speaker recognition are the foundation the rest of our product is built on.

We’re hiring a Senior Software Engineer, Voice AI (Speaker Recognition & Transcription) to join our Transcription team. You’ll focus on two things: transcription (what was said) and speaker recognition (who said it).

This is one of the most important roles at tl;dv. Every summary, insight, CRM update and AI answer we produce starts from the transcript and the speaker labels. If a word is wrong or a sentence is attributed to the wrong person, everything built on top of it is wrong too. Getting this right is what earns our customers’ trust with their most important conversations, and it’s one of our top product priorities. Your work will be felt by every user, in every meeting.

Meetings are messy: noisy audio, short turns, people talking over each other, many languages.

Your tasks

The Role

Your job is to make our transcripts and speaker attribution more accurate, faster and more scalable, and to prove it with numbers.

This is a hands-on role with a lot of autonomy. You’ll own problems end-to-end, from reading the latest specs to shipping in production and measuring the results.

You’ll report to the CTO and work closely with Product, Infra, QA and Support.

What you’ll own

Speaker Recognition

  • Own our speaker recognition and diarization systems end-to-end, from model choice to production.
  • Make them robust to real meetings: noisy audio, short turns, overlapping speech, several languages.
  • Evaluate and bring in better speaker models (open-source or in-house) when they beat what we have.

Transcription

  • Improve transcript quality across our speech-to-text models and meeting platforms: accuracy, speaker attribution, punctuation, custom vocabulary and multilingual support.
  • Help decide which model runs where, balancing quality, latency and cost.

Evaluation & Benchmarks

  • Build and own our evaluation framework: datasets and metrics for transcription and speaker recognition. Every model change should be measured, not guessed.

Scale & Production

  • Run these models in production at scale for millions of meetings, with good observability, sensible cost and no surprises.

Privacy by Design

  • Voice data is sensitive data. You’ll build with consent, data isolation and deletion in mind from day one, working closely with our security and privacy team.

Who We Are Looking For

You’ve scaled speech and voice systems in a fast-growing startup and want to do it again. You’re super hands-on and highly motivated, and you don’t need anyone to tell you what to do next. You see a problem, measure it, fix it and ship it.

Must-haves

  • Voice and speech AI expertise. Deep, hands-on experience with speaker recognition (speaker identification/verification, voice embeddings such as x-vectors or ECAPA-TDNN, diarization) and with speech-to-text models (e.g., Whisper or conformer/transducer-based ASR).
  • AI models in production. You’ve trained, fine-tuned, evaluated and deployed AI models in production. Python and PyTorch (or similar) are second nature to you.
  • TypeScript & Node.js. Solid production experience with TypeScript and Node.js. Most of our services run on them, and you’ll ship the integration around the models yourself.
  • You measure everything. You know WER, DER and EER inside out, and you’ve built evaluation pipelines and test sets that the team trusts.
  • Scale. You’ve worked on a system that scaled to millions of users, and you know what breaks at that size.
  • Startup DNA. You have experience in high-scale, fast-growing startups. You’re used to ambiguity, limited resources and moving fast without breaking quality.
  • Super hands-on. You write the code, run the experiments and debug production yourself.
  • Autonomous and ultra-motivated. You take a fuzzy problem, turn it into a plan and deliver it with little supervision.
  • 5+ years of software or ML engineering experience, including 3+ years on speech or audio models in production.
  • Fluent in English, written and spoken. You’re a strong writer and do well in a remote, async-first team.

Nice-to-haves

  • Experience with audio processing: noise reduction, voice activity detection, speech enhancement, overlapping speech.
  • Multilingual or low-resource speech experience.
  • Experience handling voice or other sensitive data under GDPR (consent, retention, deletion).
  • Event-driven architectures (message brokers, queues).
  • Hands-on experience with speech toolkits such as pyannote, SpeechBrain or NVIDIA NeMo.
  • Publications, open-source contributions or results in speech/speaker benchmarks (e.g., VoxCeleb, NIST SRE, DIHARD).

Practicalities

  • Type: Full-time
  • Engagement: We’re open to both a contractor setup and employment through an Employer of Record (EOR). We’ll figure out together what works best for you.
  • Location: Fully remote, based in Brazil
  • Ways of working: Async-first. We default to written communication (docs, RFCs, recorded walkthroughs) and keep meetings for the moments that need them.
  • Reports to: CTO

How to apply:

  • Apply directly through this job posting.

We really can’t wait to hear from you!