Backend Engineer

Company Description

Linguana is an AI technology company that automatically translates, dubs, and distributes video content globally. Our platform combines LLMs, voice synthesis, and custom translation models to preserve creator authenticity across languages. We handle the entire pipeline—from context-aware translation and voice cloning to automated distribution across YouTube, social media, and streaming platforms—enabling creators to reach worldwide audiences without manual effort. Our infrastructure processes millions of minutes of content, optimizing delivery, metadata, and monetization for each platform and market, while creators focus on content creation.

What You'll Do

• Architect and scale backend systems powering our AI-driven platform, leveraging LLMs and machine learning models for intelligent automation and content generation

• Design and implement high-performance services in Golang and Python, building robust APIs and services that handle complex flows

• Work hands-on with cutting-edge AI/LLM technologies, integrating multiple models (GPT, Claude, Gemini, open-source) to create intelligent workflows and automated pipelines

• Develop end-to-end features collaborating closely with product, AI research, and engineering teams to deliver innovative AI-powered solutions

• Research and implement state-of-the-art AI techniques, optimizing model inference, prompt engineering, and intelligent routing between different LLM providers

• Drive technical decisions with data-driven insights while balancing performance, cost, and user experience in our AI-first architecture

What We're Looking For

• 6+ years of experience architecting, deploying, and maintaining scalable, distributed backend systems

• Strong expertise in Golang and Python, with experience in frameworks like FastAPI, Gin, or Echo

• Proven experience with AI/LLM integration - prompt engineering, model APIs, vector databases, and building AI-powered applications

• Solid foundation in SQL & NoSQL databases (PostgreSQL, MongoDB, Redis) and message queuing systems

• Cloud infrastructure experience (AWS, GCP, or Azure) with containerization and orchestration (Docker, Kubernetes)

• Product-minded engineer who can translate complex AI capabilities into user-facing features, driving innovation beyond technical specifications

• Experience with AI observability, monitoring LLM performance, cost optimization, and building reliable AI systems at scale

• Strong problem-solving skills with ability to thrive in a fast-paced, AI-driven startup environment

• Bachelor's degree in Computer Science, Software Engineering, or related field

Bonus: Experience with vector databases, RAG systems, fine-tuning, or content creation/localization tools

Location: Full-time, on-site role in Tel Aviv-Yafo

Join us in building the future of AI-powered content and automation!