Senior Backend Engineer (LLM/AI Experience)

Written By Kristopher Rawcliffe

Full-time | Tech Team
📍 Barcelona (hybrid) or remote within Europe
💰 €50,000 – €65,000

threesixfive is working with a Barcelona-based AI product company that builds production-grade conversational AI systems used by enterprise customers.

The company operates at the intersection of LLMs, real-time backend systems, and cloud-native architecture, delivering intelligent AI experiences at scale rather than prototypes or experiments. Their platform is already live with paying customers and continues to grow rapidly.

As part of this partnership, we’re hiring a Senior Backend Engineer to play a key role in designing, building, and operating the backend systems that power these AI-driven experience.

In a few words

  • Build and scale backend systems powering production conversational AI

  • Hands-on senior role balancing architecture and real-world delivery

  • 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 help shape the backend foundations of a cutting-edge AI platform, where your architectural and performance decisions directly impact real-time AI experiences used by enterprise customers.

This is not an R&D or prototype-heavy role — it’s about shipping, scaling, and operating intelligent systems in production.

🚀 The Role

We’re looking for a Senior Backend Engineer with recent, real-world LLM product experience who combines strong architectural thinking with hands-on development.

You’ll work closely with senior engineering leadership, contributing to technical direction and system design, while remaining deeply involved in day-to-day coding, feature delivery, and production operations.

This is a role for someone who designs systems and builds them.

🛠️ What You’ll Do

Architecture & System Operations (≈50%)

  • Contribute to architectural decisions and backend system design

  • Collaborate with infrastructure engineers on:

    • Platform architecture

    • Observability (monitoring, logging, alerting)

    • Deployment and scaling strategies

  • Optimise system performance:

    • Latency, throughput, database queries, caching, resource usage

  • Own production operations:

    • Troubleshooting, incident response, on-call

  • Provide technical guidance through:

    • Code reviews

    • Design discussions

    • Backend best practices

  • Collaborate on real-time and streaming-oriented architectures

Feature Development & Implementation (≈50%)

  • Build and maintain backend services in production-grade Python (and Go)

  • Develop conversation-related features:

    • State management

    • History

    • Intelligence improvements

  • Implement multi-document knowledge bases and retrieval systems

  • Integrate LLM APIs and build RAG pipelines

  • Design and maintain APIs and service integrations (gRPC, REST)

  • Work on core backend services:

    • Orchestration

    • Caching

    • Platform APIs

  • Own testing, CI/CD pipelines, and deployment automation

🧰 Tech Stack

  • Python (FastAPI) and Go (gRPC services)

  • AWS (S3, EC2, Lambda, managed services, LLM platforms)

  • Docker, Kubernetes

  • RabbitMQ, Redis

  • LLM APIs (e.g. OpenAI, managed cloud LLM services)

✅ What We’re Looking For

Must-Have

  • 5+ years of backend engineering experience

  • Strong background in:

    • Distributed systems

    • Microservices

    • Real-time architectures (WebSockets, gRPC, event-driven systems)

  • Proven experience building and deploying high-performance Python services

  • 2+ years working with LLM-powered systems in production (2022–2025)

    • Hands-on use of LLM APIs

    • Experience building RAG or retrieval-based systems

  • Comfortable balancing architecture design with hands-on implementation

  • Strong AWS experience with a focus on:

    • Performance optimisation

    • Observability

    • Production reliability

  • Demonstrated ability to improve production systems:

    • Latency

    • Throughput

    • Technical debt

  • Excellent collaboration skills across backend, infrastructure, and AI-focused teams

Bonus Points

  • Golang experience

  • Experience with real-time media, streaming, or conversational platforms

  • Data engineering or ML model-serving infrastructure exposure

🎯 What Success Looks Like

First 6 Months

  • Ownership of critical backend services established

  • Knowledge transfer completed

  • Core conversation and knowledge features live in production

  • Clear performance and observability improvements delivered

First 12 Months

  • Backend services and RAG pipelines running reliably at scale

  • Platform-wide performance improvements delivered

  • Other engineers supported and unblocked through your technical guidance

  • Recognised internally as a go-to expert for backend + LLM implementation

💼 What’s On Offer

Compensation & Flexibility

  • 💰 €50,000 – €65,000, depending on experience

  • 🏠 Hybrid work in Barcelona or remote within Europe

Impact & Growth

  • Ownership of backend systems used daily by enterprise customers

  • Hands-on technical role with real architectural responsibility

  • Deep technical challenges across:

    • LLMs

    • RAG pipelines

    • Real-time systems

    • Scalability and reliability

  • High-impact role in a small, senior engineering team

  • Close collaboration with engineering, AI, and infrastructure specialists

  • Opportunity to deepen expertise in applied AI systems

Additional Perks

  • Central Barcelona office

  • Flexible remote working

  • Lunch support when in the office

  • Private health insurance

  • Travel allowance (distance-based)

  • Flexible benefits under Spanish tax legislation

  • Wellness / fitness discounts

To apply or learn more: email kris@threesixfive.es with your CV or LinkedIn profile.

Kristopher Rawcliffe
Next

Machine Learning Engineer – Real-Time Video Generation