The mission
inCall is an AI-powered receptionist for NHS GP practices. Patients call in, the AI verifies their identity against NHS records, routes their call, and eventually handles the whole conversation start to finish. Before committing to permanent on-premises infrastructure, Ladybird is running a cloud-based proof of concept to prove the architecture works at NHS scale. You are building that POC. Three months, real monthly deliverables, accepted in writing before you are paid.
The stack
3CX - number, SIP trunk connecting 3CX to FreeSWITCH on AWS EC2 | FreeSWITCH on EC2 across eu-west-2a and eu-west-2b | AWS VPC eu-west-2, dual-AZ, NLB, Route 53 failover, Lambda, API Gateway | AWS Lambda connecting to NHS PDS FHIR API for patient verification (sandbox now, live pending NHS approval) | OpenAI GPT for POC AI layer (substitution for the target on-premises fine-tuned LLaMA model) | AWS Transcribe (en-GB) and ElevenLabs for STT/TTS | MongoDB for data | React receptionist dashboard with live call monitoring and verification status
What you'll build
Month 1 - 3CX configured and SIP trunk to FreeSWITCH live. Dual-AZ VPC deployed. First inbound call end-to-end confirmed. NHS PDS FHIR Lambda deployed and logging to CloudWatch.
Month 2 - Full 3CX IVR with DTMF, verification, queue, and out-of-hours voice routing. OpenAI, Transcribe and ElevenLabs integrated. CloudWatch/S3 audit logging correct. AZ failover confirmed.
Month 3 - Full end-to-end POC demo. Stage 1 receptionist React app delivered. CTI event layer built. POC-to-production migration plan documented.
What you bring
Solid hands-on AWS - VPC, EC2, Lambda, API Gateway, IAM, CloudWatch, S3. SIP/PBX experience - 3CX preferred, FreeSWITCH or Kamailio on Linux essential. Python for Lambda and integration glue. React for the Month 3 dashboard. Terraform and GitLab CI/CD. Understanding of NHS data handling - patient PII in logs, API audit trails. Available for 12:00 GMT daily standups and responsive within 4 hours on Working Days. Ability to own deliverables with no hand-holding - monthly acceptance criteria are fixed.
The bigger picture
This is Stage 1 of a four-stage product. Stage 2 adds AI triage and auto-routing. Stage 3 adds clinical routing support. Stage 4 is a fully autonomous AI call handler. Commercial model is cost-per-call licensing across GP practices. A cloud engineer who delivers a clean, well-documented POC is well-placed for the next contract.
Don't apply if
You need to be told what to do each day. You are currently engaged in other contracts that will compete for your time. You cannot commit to the daily standup and monthly deliverable rhythm. You have never touched SIP or telephony infrastructure and are not willing to learn it fast.
How we hire
We receive far more applications than we can interview.
- Application form - personal information, professional screening, and five written responses answered thoroughly.
- Video submission - if selected you will receive an email within 5 working days with specific requirements. 48 hours to submit.
- Group interview - live Google Meet session with other shortlisted candidates.
- One-to-one - deep technical and delivery interview covering AWS architecture, 3CX/SIP, NHS data handling, and your approach to the inCall POC specifically.
- Offer and contract - full contract with Key Contract Information summary included.
To apply: Submit your CV above, then complete our full application form at:
https://ladybirdltd.jp.larksuite.com/share/base/form/shrjpDZA9DO28tKsWj8Al9ikbob
Your Indeed application alone is not sufficient - applications without the completed form will not progress.
Pay: £700.00-£3,000.00 per month
Work Location: Remote
