Backend Software Engineer - AI Assist
Telavox ABJobbet i korthet
Anställningstyp
tillsvidareanstallning
Arbetstid
heltid
Ansök senast: 2027-03-23
Publicerad: 2026-09-24
Beskrivning
Join Telavox as a Backend Software Engineer - AI Assist 🤖
Are you a backend engineer who wants to see AI run in production, not in a demo? AI Assist turns every recorded phone call on the Telavox platform into a transcript, a summary and action items for the people who took the call. We are looking for an engineer who is at home where distributed systems, telephony, and large language models meet.
In this role, placed in Malmö or Stockholm, you'll build and run the services behind AI Assist: turning a finished call into text and insight, and delivering the result to our apps and our admin portal. You'll work in a small team with a lot of ownership, shaping what to build together with the product manager day to day, and what you ship reaches real customers and partners the same week.
If you'd like to take the next step in your career and are excited by the challenge of making AI dependable at scale, this is your opportunity!
About the job
AI Assist is live today, sold both directly and through telecom operators across Europe, and usage is growing month over month. You'll join the team that owns it end to end, from the transcription pipeline to the APIs our apps and customers use. Much of the work is classic backend engineering with an AI twist: asynchronous processing, third-party model APIs, access control, metering, and data that has to be handled correctly under GDPR and EU data-residency requirements.
You'll work side by side with a colleague focused on model evaluation and transcription quality, with the AI Agents team next door building our AI agent platform, and with the telephony, apps and platform teams whose systems yours plug into.
Our stack: Java and Spring Boot, Kubernetes, and Google Vertex AI with Gemini and other model providers for transcription and analysis.
Your day-to-day work may include:
Designing, implementing and testing new capabilities in the AI service, from summaries a customer can shape themselves to the controls an admin needs to roll the product out.
Evolving the transcription pipeline together with the telephony and platform teams.
Integrating LLM and speech APIs in a production setting: asynchronous processing, quotas and rate limits, and keeping data within the EU.
Building the APIs that serve transcripts to our apps, our admin portal and our customers, with access control and data retention done right.
Owning what you ship: observability, alerting, and the follow-up when something fails.
About you
You're a product-minded backend engineer who likes owning a service from design to production, and who is comfortable in a system that spans several teams and a telephony platform with two decades of history. You care about correctness where it matters (who may read what, what is stored for how long, what a customer is billed for), and you enjoy the pace of a small team with customers and partners waiting for what you build. You don't need to be an AI researcher. You need to be the engineer who makes AI dependable.
Key skills and experience we're looking for:
Several years building backend services in Java, preferably with Spring Boot
Strong understanding of REST APIs, asynchronous processing, and system integration across service boundaries
Experience running services in production: monitoring, observability, and debugging in a distributed system
Experience with relational databases and queue-based or job-based architectures
Proficient in English, both spoken and written
Good-to-have skills:
Python, which we use alongside Java across the AI domain
Experience calling LLM or speech-to-text APIs from production code (Gemini, OpenAI or similar)
Experience deploying and running services on Kubernetes
Familiarity with telephony concepts (SIP, call recording, PBX) or with GDPR and data-residency requirements in practice
Join us at Telavox 💚
Since Telavox's journey started in 2002, we have strengthened our position as the leading forward-thinking communication platform for businesses. As a digital mobile operator, we develop and own our all-in-one communication platform, which integrates telephony, PBX, messaging, meetings, and contact centers, giving businesses a smarter way to connect.
Today, we're a thriving company with 1.9 billion SEK in revenue and 500+ Telavoxers across nine countries. We embrace AI and automation to push the boundaries of business communication.
We offer flexible work options and adaptable hours, giving you the freedom to balance life and career while staying connected to our vibrant Telavox culture.
Read more about our new HQ in Malmö 🏠!
How to apply!
At Telavox, we don't focus on fitting in; we focus on making room for everyone.
We're always on the lookout for great talent, so applications are reviewed continuously. If you're ready to be part of an innovative, AI-driven telecom company, apply today with your CV and cover letter in English.
Learn more about what we do! ⬇️
Are you a backend engineer who wants to see AI run in production, not in a demo? AI Assist turns every recorded phone call on the Telavox platform into a transcript, a summary and action items for the people who took the call. We are looking for an engineer who is at home where distributed systems, telephony, and large language models meet.
In this role, placed in Malmö or Stockholm, you'll build and run the services behind AI Assist: turning a finished call into text and insight, and delivering the result to our apps and our admin portal. You'll work in a small team with a lot of ownership, shaping what to build together with the product manager day to day, and what you ship reaches real customers and partners the same week.
If you'd like to take the next step in your career and are excited by the challenge of making AI dependable at scale, this is your opportunity!
About the job
AI Assist is live today, sold both directly and through telecom operators across Europe, and usage is growing month over month. You'll join the team that owns it end to end, from the transcription pipeline to the APIs our apps and customers use. Much of the work is classic backend engineering with an AI twist: asynchronous processing, third-party model APIs, access control, metering, and data that has to be handled correctly under GDPR and EU data-residency requirements.
You'll work side by side with a colleague focused on model evaluation and transcription quality, with the AI Agents team next door building our AI agent platform, and with the telephony, apps and platform teams whose systems yours plug into.
Our stack: Java and Spring Boot, Kubernetes, and Google Vertex AI with Gemini and other model providers for transcription and analysis.
Your day-to-day work may include:
Designing, implementing and testing new capabilities in the AI service, from summaries a customer can shape themselves to the controls an admin needs to roll the product out.
Evolving the transcription pipeline together with the telephony and platform teams.
Integrating LLM and speech APIs in a production setting: asynchronous processing, quotas and rate limits, and keeping data within the EU.
Building the APIs that serve transcripts to our apps, our admin portal and our customers, with access control and data retention done right.
Owning what you ship: observability, alerting, and the follow-up when something fails.
About you
You're a product-minded backend engineer who likes owning a service from design to production, and who is comfortable in a system that spans several teams and a telephony platform with two decades of history. You care about correctness where it matters (who may read what, what is stored for how long, what a customer is billed for), and you enjoy the pace of a small team with customers and partners waiting for what you build. You don't need to be an AI researcher. You need to be the engineer who makes AI dependable.
Key skills and experience we're looking for:
Several years building backend services in Java, preferably with Spring Boot
Strong understanding of REST APIs, asynchronous processing, and system integration across service boundaries
Experience running services in production: monitoring, observability, and debugging in a distributed system
Experience with relational databases and queue-based or job-based architectures
Proficient in English, both spoken and written
Good-to-have skills:
Python, which we use alongside Java across the AI domain
Experience calling LLM or speech-to-text APIs from production code (Gemini, OpenAI or similar)
Experience deploying and running services on Kubernetes
Familiarity with telephony concepts (SIP, call recording, PBX) or with GDPR and data-residency requirements in practice
Join us at Telavox 💚
Since Telavox's journey started in 2002, we have strengthened our position as the leading forward-thinking communication platform for businesses. As a digital mobile operator, we develop and own our all-in-one communication platform, which integrates telephony, PBX, messaging, meetings, and contact centers, giving businesses a smarter way to connect.
Today, we're a thriving company with 1.9 billion SEK in revenue and 500+ Telavoxers across nine countries. We embrace AI and automation to push the boundaries of business communication.
We offer flexible work options and adaptable hours, giving you the freedom to balance life and career while staying connected to our vibrant Telavox culture.
Read more about our new HQ in Malmö 🏠!
How to apply!
At Telavox, we don't focus on fitting in; we focus on making room for everyone.
We're always on the lookout for great talent, so applications are reviewed continuously. If you're ready to be part of an innovative, AI-driven telecom company, apply today with your CV and cover letter in English.
Learn more about what we do! ⬇️
Ansök till tjänsten
Backend Software Engineer - AI Assist
OM FÖRETAGET
Telavox AB
