Backend Team Leader - GenAI

About Ludeo

Ludeo is a next-generation content platform for gamers where users can actually play the posts they see.

It is based on innovative proprietary technology that enables anyone to clip their most exciting game highlights and turn them into standalone game pieces called “Ludeos.” These Ludeos can be shared so that others can instantly play to create their own outcomes and experiences.

About the Role

We are seeking a Backend Team Lead to spearhead the development of ludeo.ai, our GenAI-powered product that enables users to generate interactive “Ludeos” (gaming experiences) directly from prompts or video content. This is a high-impact leadership role at the intersection of backend architecture, multimodal AI, and real-time systems. You will architect and lead the AI engine that transforms unstructured inputs (text/video) into structured, interactive gaming playable moments.

What You’ll Do

Lead & Mentor: Build and manage a high-performing backend/AI engineering team, drive architectural decisions, and foster rapid innovation while maintaining production-grade reliability.
Design AI-Native Systems: Architect scalable microservices powering complex AI workflows. Design and implement Retrieval-Augmented Generation (RAG) pipelines, embedding strategies, and vector database infrastructure (e.g., Pinecone, Weaviate, Milvus, PGVector). Optimize retrieval, prompt orchestration, latency, and cost.
Agentic Workflows: Design multi-agent systems using planner/executor/tool-calling patterns. Implement stateful, multi-step AI workflows with frameworks such as LangChain, CrewAI, AutoGen, or similar. Build evaluation, observability, and safety mechanisms for LLM systems.
Multimodal AI: Integrate multimodal models (vision + text) to understand video and translate it into structured form.
Scale & Infrastructure: Ensure robustness, security, and high availability on AWS/Kubernetes. Design distributed systems that handle real-time data and AI workloads efficiently.
Collaborate: Work closely with Product and Design to translate GenAI capabilities into stable, scalable production features.

Requirements:

Expreince leading engineering teams in fast-paced environments with strong ownership and architectural responsibility.
Backend Expertise: 6+ years of backend development experience with deep expertise in Node.js and microservices. Strong distributed systems and API design experience.
GenAI Systems Experience: Hands-on experience building production LLM systems. Proven experience with RAG architectures, vector databases, embedding pipelines, and prompt orchestration. Experience designing multi-step or agentic AI workflows.
Infrastructure: Strong experience with AWS and Kubernetes in production environments. Deep knowledge of SQL & NoSQL systems.
Communication: Ability to translate complex AI systems into clear product and business decisions.

Preferred Qualifications

Strong Python proficiency, particularly in AI/ML production environments
Hands-on experience with multimodal LLMs (vision-language models) and processing pipelines for image/video + text
Experience designing autonomous or semi-autonomous AI systems (planner/executor architectures, tool-calling, long-running agents)
Experience evaluating and benchmarking LLM systems (quality, hallucination mitigation, latency, cost optimization)
Strong DevOps capabilities including Docker, CI/CD pipelines, and deploying AI services/models to production