Senior Software Engineer - Runtime Team
Poly AI is hiring a Senior Software Engineer - Runtime Team in London, United Kingdom. Level rates it ; you can apply on Poly AI.
Level's read on this job
- Level rates this software engineer role Works on AI ●●●○: the daily work is on AI products, without building the model.
- Tools and skills the posting cites include AI agents and speech.
- Level classifies it as a senior role.
- Level lists 2 other open roles at Poly AI.
- The role was posted in the last few days.
AI in this role
PolyAI is the Agentic Dialog Platform for building the conversational enterprise, used to build, run, govern, and improve dialog agents at scale. Powered by Raven, a proprietary dialog model trained on more than a billion enterprise conversations, PolyAI agents are built for complexity, open at every layer, and sovereign by design. PolyAI serves hundreds of enterprises across 75 languages and 25 countries, including Metro Bank, Marriott, PG&E, and UniCredit.
We're looking for a Senior Software Engineer to join the Runtime team at PolyAI. This team owns the core voice infrastructure that powers every call our AI agents handle - from the moment a phone rings to the moment it hangs up.
You'll work across the full real-time voice stack: telephony, real-time audio streaming and media handling, speech recognition and synthesis integration, LLM orchestration, turn-taking and voice activity detection, call recording, and the data pipeline that captures it all. We operate across AWS and Azure, serving enterprise customers at scale across multiple global regions.
What You'll Do:
- Design and build features across the voice runtime - from new integrations with third-party contact centre platforms, to improving how our agents handle interruptions and overlapping speech, to scaling our infrastructure for higher call volumes.
- Own services end-to-end: write code, review PRs from across the company, deploy to production, and support what you ship.
- Debug complex, cross-service issues in production - the kind where a timing problem involves VAD thresholds, ASR transcription windows, LLM response latency, and audio playback all interacting at once.
- Contribute to architecture decisions and design documents. The team has strong thought leadership on stateful vs stateless service boundaries, API design, and where responsibilities should live.
- Collaborate with product facing teams who build on top of the runtime - helping them understand configuration, troubleshooting call behaviour, and unblocking their work.
- Improve the developer experience: better defaults, less reliance on opaque config, more features controllable through the UI, and better test coverage.
What We're Looking For
Must have:
- 4+ years of commercial software development experience.
- Strong experience with real-time or latency-sensitive systems: streaming, media pipelines, networking, or similar domains where milliseconds matter.
- Solid understanding of distributed systems: gRPC, state management across services, connection error recovery, and working with systems that must not drop calls.
- Experience with cloud infrastructure on AWS (EKS/Kubernetes, Lambda, S3, DynamoDB, Redis) - comfortable deploying containerised services and debugging infrastructure-level issues.
- Strong written communication - design docs, PR reviews, and async debugging are core to how the team works.
Strong plus:
- Experience with speech technologies: ASR, TTS, VAD, or end-of-turn detection — either integrating them or working on the systems around them.
- Experience with Go - this is the primary language for our voice services. Most engineers on the team work across both Go and Python.
- Experience with Python - parts of our LLM orchestration layer, serverless function runtime, and data pipeline are Python.
- Prior work on LLM orchestration or agent frameworks: tool calling, function execution, prompt management, context window management, or conversation state machines.
- Experience with data pipeline technologies: Kafka, ClickHouse, S3-based event stores, or similar.
- Experience with observability at scale: Datadog, structured logging, SLO/SLI definition, and using metrics to drive reliability improvements.
- Multi-cloud experience (Azure in addition to AWS).
- Familiarity with VoIP/telephony (SIP, RTP) or WebRTC (STUN/TURN/ICE, media negotiation).
Benefits
💰 Participation in the company’s employee share options plan
🏝 Tenure-Based PTO: You will receive 25 holidays when you join and will gain an additional 1 day after 2 years of service, then 1 day each year until capped at 32 holidays
🏡 Flexible working from home policy
🌎 Work from outside of the UK for up to 6 months each year
🫂TELUS Health EAP 24/7 - offers you and your chosen family confidential, judgment-free support for any work, health, or life challenge
🧡 Enhanced parental leave
🚲 Bike2Work scheme
📚 Annual learning and development allowance
🏡 We’re all about making WFH work for you - that’s why we offer a one-off WFH allowance when you join. Offering perks like noise-cancelling headphones or a comfortable desk chair to boost your comfort and focus!
👨👩👧 Company-funded fertility and family-forming programmes
🌸 Menopause care programme with Maven
🏥 Private healthcare and dental cover, discounts on gym members and relaxation apps, and access to a range of mental health programs
🌎 Sabbatical Program: 5-week paid sabbatical available after 5 years of employment
At PolyAI, we take great pride in our values - they guide everything we do. We believe that a strong culture leads to meaningful work and lasting impact.
Our core values are:
Only the best
We expect the best from our people, we hire people that expect the best from themselves, and we nurture this drive for excellence.
Ownership
We care deeply about what we do. We take ownership of our initiatives, decisions and outcomes.
Relentlessly improve
We demand more from ourselves and are always evolving. Continuous, obsessive improvement is the only way we will transform the world of conversational AI.
Bias for action
Our world moves quickly and so do we. We take calculated risks and we deliver impact fast.
Disagree and commit
We are all working toward the same goal. If we donʼt agree with something, we work hard to understand it and when a decision is made, we accept it and give it our all.
Build for people
We want the world to enjoy the experiences they have with us. We are building for a future that prefers automation.
PolyAI is proud to be an equal-opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. All employment decisions at PolyAI will be based on the business needs without attention to ethnicity, religion, sexual orientation, gender identity, family or parental status, national origin, neurodiversity status or disability status.
Kindly find the Privacy Notice for our recruitment process by following the link here. This document provides important information regarding how we handle your personal data throughout the recruitment journey.
How we rate this
Senior Software Engineer - Runtime Team at Poly AI rates 68 out of 100 for how much of the daily work is AI. That makes it Works on AI (AI Level 3 of 4). The level is about AI in the job, not seniority.
Works on AI. The daily work is on AI products, without building the model.
- ●●●● Builds AI80 to 100
- ●●●○ Works on AI60 to 79
- ●●○○ Uses AI40 to 59
- ●○○○ Little AI0 to 39
Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.
Prepare for this job
Built from this posting and from similar jobs on Level.
Skills and AI tools this role asks for
Also common in software engineer jobs at this level
Pay
- Typical software engineer job
- $167k
This posting doesn't list pay. Use the typical software engineer figure when pay comes up. See software engineer jobs
Questions you could be asked
- How do you decide when an AI agent can act on its own versus asking for approval first?
- What have you built with speech recognition or text-to-speech, and where did it break?
- Describe a typical day in a role like this one: which parts run through AI directly?
- If you removed AI from this role, what would be left, and how do you decide what still needs a human?
Adapt your resume
- List these exact terms on your resume: AI agents and Speech. An applicant tracking system matches the wording, not the idea.
- Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
- Show where AI is part of your daily process, not a one-off project. This role expects it to be a running habit.
Get your CV reviewed before you apply
Send your CV and the role you want next. Your review arrives by email within 3 days.
Get new software engineer jobs (Works on AI ●●●○ or higher) by email
One email a week, each job rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.
Free.
Similar roles
Software Engineering roles that work on AI, at other companies.
What kind of AI work fits you?
Answer 12 practical questions in about three minutes. Get a simple profile, the work it points to, and live roles to explore next.
Find my next step