Senior Backend Engineering

Job Description This is a remote position. Location : Remote Engagement Type : Project-based Assignment; B2B Contract (Outside IR35) Duration : 6 months with auto renew Timezone : CET ± 3 hours Be part of our Global Engineering Network! One of our clients in the AI and Software sector is looking for an experienced Backend Engineer to join their core development team. He/She will be responsible for building low-latent infrastructure that orchestrates audio/video sessions, integrates AI services (speech + LLMs), and powers APIs used by our mobile and web applications. Key Deliverables- Build, deploy, and manage the real-time communication backend to support live audio interactions Orchestrate end-to-end sessions between end users and backend AI services Integrate Azure Speech services (STT/TTS) and Azure OpenAI (LLMs) into real-time pipelines Develop and maintain REST and WebSocket APIs consumed by mobile and web frontends Handle session state, participant matching, reconnections, and failure recovery as the “traffic controller” for calls Ensure low-latency, highly available, and scalable infrastructure using containerized microservices Build backend logic to manage call lifecycle (start/end sessions) Match participants and track call state Implement reconnection and failure-handling mechanisms Act as the system’s “traffic controller” for real-time media sessions Azure Services Azure Speech: Speech-to-Text (STT) and Text-to-Speech (TTS) Applied to transcription, voice bots, and real-time voice AI Azure OpenAI: Integration of LLMs (e.g., GPT) for conversational logic, AI assistants, summaries, and insights Azure Container Apps: Host scalable backend services in containers Support for microservices architecture and API scaling API Development Build RESTful APIs for authentication, call setup, and control Implement WebSocket endpoints for real-time signaling Requirements Ideal Profile 5+ years of backend engineering experience Strong background in: Distributed systems Networking fundamentals (TCP/UDP, NAT, firewalls) Cloud infrastructure (Azure preferred, but AWS/GCP experience considered) Proven experience with WebRTC or similar real-time systems (e.g., SIP, RTMP, low-latency streaming) Experience integrating AI/LLM services into production backends Ability to work autonomously and mentor junior engineers as needed Deep understanding of WebRTC connectivity (NAT traversal, firewalls, corporate networks) Experience with TURN server deployment and management for media relaying Proficiency in one or more of: Node.js, Python, .NET Ability to handle audio routing, recording, and optional voice transformations Hands-on experience with media servers such as: Janus Kurento mediasoup Preferred Skills Experience with Kubernetes and service meshes Familiarity with Terraform or other IaC tools Background in audio processing or voice transformation pipelines Contributions to open-source WebRTC projects Why Partner with Us? · Clear scope with no ambiguity over deliverables. · Opportunity for repeat engagements based on performance. Selection Process 1. Proposal Submission o Submit your professional profile/CV by applying for the role. 2. Business Alignment Call o 30-minute virtual discussion with a Human Capital Consultant to review scope and expectations. 3. Verification o Opportunity to complete Castille Vetting (background and compliance checks). 4. Client Skills Review o Direct interview with the end client to discuss project specifics. o Project-specific technical assessment (if required). Ongoing Business Support · Access to CX guidance and market insights through our professional network.