Who we are
Xenoss is an AI engineering and integration services company, helping medium to large enterprises run AI transformation end-to-end, from situation analysis and goals framing to data discovery and preparation, pipeline building, model development, solution deployment, and support.
We build a broad spectrum of AI solutions such as user behaviour prediction, content generation, NLP, audience segmentation, AI assistants, edge computer vision, fraud detection, and others.
We work with prominent companies such as Microsoft, Toshiba, AstraZeneca, Activision Blizzard, Verve Group, Voodoo Games, and Telefonica, among others.
We’re included in the top 100 software companies on the Inc. 5000 list.
What is the project
We’re hiring a Senior Full-Stack Engineer to join a long-term In-Call Assistant initiative for a world-leading financial services company.
The project focuses on building a real-time conversational AI system that supports front-office employees during live customer conversations. The system identifies relevant conversation signals and provides concise, context-aware recommendations.
You will primarily work on the application and integration layer connecting live conversation data, AI models, enterprise data sources, backend services, and the employee-facing web interface.
The broader solution includes real-time transcription, signal detection, context preparation, recommendation generation, RAG, feedback capture, and production monitoring.
What will you do
You’ll build and integrate the application layer around the AI models, working closely with the AI Solution Architect, AI engineers, MLOps, and client engineering teams.
Core work includes:
Building backend services and APIs for the real-time In-Call Assistant
Building the employee-facing web UI for presenting recommendations and conversation context
Implementing real-time data flows from conversation input to recommendation delivery
Integrating transcription, AI inference, CRM, customer context, and internal APIs
Implementing the context-preparation and orchestration layer between system components
Implementing feedback capture for recommendation acceptance, dismissal, and user actions
Handling authentication, authorization, logging, and enterprise integration requirements
Optimizing application performance, reliability, and end-to-end latency
Supporting deployment, observability, and production troubleshooting
The proposal explicitly includes a context-preparation harness, real-time inference pipeline, UI delivery, feedback capture, and deployment/handover as core solution components.
Technology landscape
You’ll operate across a modern cloud and AI application stack, including:
Python and/or TypeScript
React or similar modern frontend frameworks
FastAPI, Node.js, or equivalent backend frameworks
REST and streaming APIs
WebSockets, Server-Sent Events, or similar real-time communication patterns
Event-driven and asynchronous processing
Integration with AI/ML inference services
Enterprise API and data integrations
Authentication and authorization
Logging, tracing, and observability
Containerized deployment and CI/CD
Cloud infrastructure and managed services
We optimize for reliability, low latency, maintainability, and enterprise constraints.
Scope of ownership and delivery context
Core ownership
Build the application layer connecting AI models with enterprise systems
Build and evolve the employee-facing web UI
Implement real-time APIs and orchestration flows
Integrate customer, CRM, product, and policy context into the AI pipeline
Implement recommendation delivery and feedback capture
Ensure application-level reliability, observability, and performance
Support transition from offline prototype to live pilot and production
Team and delivery context
Work closely with the AI Solution Architect and two AI/ML engineers
Collaborate with client backend, infrastructure, security, and integration teams
Integrate with syst
