Senior Software Engineer, Backend (Generative AI)

About Pocket FM

At Pocket FM, we’re an AI-powered entertainment company using technology to help creators build and scale stories globally. We have 250M+ listeners, 550K+ creators, and 770K+ original stories, with 105B+ minutes streamed annually. Our stories have also grown into major entertainment franchises, including 96 million-dollar and 13 ten-million-dollar titles.

Introducing Pocket Saga – The Future of AI-Powered Video Storytelling

As the next chapter of our journey, we're building Pocket Saga, Pocket Entertainment's AI-powered video entertainment platform.

Pocket Saga is transforming how stories become videos by enabling creators to convert written stories into high-quality vertical video using AI. Today, the platform features 100+ anime and live-action titles across fantasy, romance, drama, and more, and has been growing at nearly 100% month-on-month.

Our vision is simple: every great storyteller should be able to create compelling video content, without needing an entire production studio.

To achieve this, we're building a creator-first AI platform that makes vertical movie-making simple, scalable, and accessible while maintaining high creative quality.

What We're Building

We're developing the next generation of AI-native entertainment infrastructure, including:

• An end-to-end platform for transforming stories into vertical video.
• AI-powered workflows for generating and maintaining consistent characters, worlds, scenes, and story continuity.
• Intelligent tools that assist creators with emotionally engaging storytelling.
• Large-scale backend systems that power AI-driven image, video, and voice generation.
• Cost-efficient AI inference infrastructure capable of serving hundreds of thousands of creators.
• The next generation of AI-native entertainment production.

far more than an AI video tool

We operate at a massive global scale while maintaining a startup mindset curious, fast-moving, and deeply owner-driven. At Pocket FM, engineers are encouraged to think boldly, solve challenging technical problems, and build products that redefine the future of storytelling.

Role Overview

We're looking for a Senior Backend Engineer to join our AI/ML Platform Team, building the backend infrastructure that powers AI-driven content creation across text, speech, image, and video generation.

You'll work on highly scalable backend systems, distributed services, AI orchestration, and cloud-native infrastructure that support next-generation AI-powered entertainment experiences.

Key Responsibilities

• Develop and maintain backend services, APIs, and microservices using Python or Go.
• Build AI-powered backend systems supporting LLMs across speech, text, image, and video generation.
• Design scalable backend components that power AI features in production.
• Participate in architecture discussions, code reviews, documentation, CI/CD, and mentor junior engineers.
• Drive engineering best practices, code quality, testing, and maintainability.
• Improve performance, reliability, scalability, and security of backend services.
• Integrate backend services with cloud infrastructure, databases, caching, and storage systems.
• Collaborate with AI/ML engineers to integrate LLM APIs and support large-scale inference workflows.
• Write clean, maintainable, well-tested production code.
• Define and monitor GenAI metrics such as latency, token consumption, hallucination rates, and retrieval quality.

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Software Engineering, or a related field.
• 3–5 years of backend software engineering experience.
• Strong programming skills in Python or Go.
• Experience building APIs, backend services, and microservices.
• Familiarity with backend frameworks such as FastAPI, Flask, Gin, or Echo.
• Good understanding of REST APIs; exposure to gRPC or GraphQL is a plus.
• Experience with SQL databases (MySQL/PostgreSQL), NoSQL databases (MongoDB/Cassandra/Scylla), and Redis.
• Interest or experience working with AI systems, LLMs, and backend infrastructure.
• Strong problem-solving ability and ownership mindset.

Nice-to-Have Skills

• Experience working with vision language models (VLMs) for visual intelligence tasks
• Experience with vector databases such as Pinecone, FAISS, or Weaviate.
• Hands-on experience with OpenAI, Anthropic, Gemini, or similar LLM APIs.
• Docker and containerization experience.
• Cloud experience on AWS, GCP, or Azure.
• Familiarity with CI/CD pipelines and observability tools such as Prometheus, Grafana, or Datadog.
• Experience with LangChain, LlamaIndex, or similar orchestration frameworks.
• Hands-on experience with RAG pipelines, vector search, agentic AI systems, and LLM orchestration.
• Strong understanding of distributed systems, caching, observability, and cloud-native architectures.

https://xtra.pocketfm.com/