### **Senior Backend Engineer (LLM / AI Experience)** **Hybrid · Tech Team · Full\-time** Barcelona, Spain ### **In a few words** * Build and scale **backend systems powering conversational AI \& digital humans** * Hands\-on senior role balancing **architecture \+ production code** * Work deeply with **LLMs, RAG pipelines, and real\-time systems** Barcelona (hybrid) or remote in Europe \|* €50k–€65k **Why this role is exciting:** You’ll shape the backend foundations of a cutting\-edge digital human platform, where your architectural and performance decisions directly impact real\-time AI experiences used by enterprise customers. ### **About UNITH** At **UNITH**, we’re transforming customer journeys with conversational AI. Listed on the ASX, we create **lifelike digital humans** using cutting\-edge synthetic facial movement, voice engineering, and conversational design. Our digital humans speak **60\+ languages** with **600\+ voices**, redefining how businesses interact with customers worldwide. ### **The Role** We’re looking for a **Senior Backend Engineer with recent LLM product experience** who combines strong architectural thinking with hands\-on development. You’ll work closely with the **Head of Engineering**, playing a key role in technical decisions while remaining deeply involved in day\-to\-day coding, feature delivery, and system optimization. You’ll be a senior technical voice on the team — someone who designs systems and builds them. ### **️ What You’ll Do** ### **Architecture \& System Operations (50%)** * Actively participate in architectural decisions with the Head of Engineering * Collaborate with the Cloud Infrastructure Engineer on platform architecture, observability (monitoring, logging, alerting), and deployment strategies * Design and optimize systems: performance profiling, database queries, caching, and resource usage * Own production operations: troubleshooting, incident response, and on\-call * Provide technical guidance through code reviews, design discussions, and best practices * Collaborate on real\-time streaming architecture with the Video Synthesis Engineer ### **Feature Development \& Implementation (50%)** * Implement backend features and services in production\-grade **Python and Go** * Build conversation features: state management, history, and intelligence improvements * Implement multi\-document knowledge bases using **AWS Bedrock** * Integrate LLM APIs (OpenAI, AWS Bedrock) and build **RAG pipelines** * Develop APIs and service integrations (gRPC, REST) * Work on core backend services: orchestration, caching, and platform APIs * Own testing, CI/CD pipelines, and deployment automation ### **Tech Stack** * Python (FastAPI) and Go (gRPC services) * AWS (S3, EC2, Lambda, Bedrock, managed services) * Docker, Kubernetes, RabbitMQ, Redis * LLM APIs (OpenAI, AWS Bedrock) ### **✅ What We’re Looking For** ### **Must\-Have** * 5\+ years of backend engineering experience with distributed systems, microservices, and real\-time architectures (WebSocket, gRPC, event\-driven) * Experience building and deploying complex, highly\-performant Python applications * 2\+ years building **LLM\-powered products in production** (2022–2025\), including hands\-on experience with LLM APIs (OpenAI, Anthropic, AWS Bedrock) and RAG systems * Comfortable balancing architecture design with hands\-on implementation * Strong AWS experience with focus on performance optimization, observability, and production operations * Proven ability to optimize production systems (latency, throughput, technical debt) * Excellent collaboration skills across backend, infrastructure, and AI/ML teams ### **Bonus Points** * Golang experience * Experience with video streaming, media processing, or conversational AI platforms * Data engineering or ML model serving infrastructure experience ### **What Success Looks Like** **First 6 months** * Knowledge transfer completed and ownership of critical backend services established * Multi\-document knowledge base and conversation features live in production * Active contributor to architecture discussions with measurable performance improvements * Production systems well\-monitored with improved observability **First 12 months** * Core backend services and RAG pipeline running reliably in production * Platform\-wide performance optimizations delivered (Q1–Q3 targets met) * Backend engineers unblocked and supported through your technical guidance * Recognized as the go\-to expert for backend \+ LLM implementation ### **What We Offer** ### **Compensation \& Flexibility** * Salary: **€50,000 – €65,000**, depending on experience * Hybrid work in Barcelona or remote options within Europe ### **Impact \& Growth** * Ownership of critical backend services used daily by enterprise customers * Hands\-on technical work alongside architectural responsibility * Deep technical challenges across LLMs, RAG pipelines, real\-time systems, and scalability * High\-impact role in a **small, senior team (12 people)** * Close collaboration with Engineering, AI research, and infrastructure teams * Opportunity to build expertise in the fast\-evolving digital humans domain ### **Additional Perks** ️ Office in the center of Barcelona Work from anywhere ️ Lunch compensation when in the office Private health insurance with Alan Travel allowance (for team members living 10km\+ from the office) Flexible benefits (tax\-free under Spanish legislation) ️ ClassPass discount ### **How to Apply:** Submit: * Your CV highlighting **ML production experience** * A short motivation (3–5 sentences) covering: * Backend systems you’ve built and maintained * LLM features you’ve implemented in production * A performance optimization project you worked on * Your experience with RAG or knowledge bases * Why digital humans excite you Apply via the **Easy Apply** button, or reach out directly to **joyce@unith.ai** — creativity is welcome ### **Recruitment Process** 1\. Intro call with Joyce (30 min) 2\. Technical interview with Head of Engineering \& Product Manager (90 min) 3\. Team meeting with backend video synthesis, and/or infrastructure engineers (90 min) 4\. Practical exercise (short, relevant implementation task) 5\. Reference check * ️ **Timeline:** 2–3 weeks from application to offer **Ready to make digital humans faster, better, and more reliable?** Apply now