Senior Backend & ML Engineer – Social Feed Architecture

Tech Stack: Python, AWS Cloud, Vector Databases, Modern AI/ML Tools, Redis, PostgreSQL/DynamoDB

About the Role

We are building a next-generation AI-driven social platform combining high-engagement short-form video feeds with intelligent product recommendations and discovery.

We are looking for a Senior Backend & Machine Learning Engineer who understands what it takes to power a low-latency, high-throughput social feed. You will sit at the intersection of core distributed systems architecture and modern ML recommendation pipelines, owning the engine that drives user engagement across our platform.

Whether you thrive in our El Segundo, CA office or work remotely within PST-aligned time zones, you will have direct ownership of one of the most critical systems in our product stack.

What You’ll Do

• Architect & Scale Feed Infrastructure: Design, build, and optimize our high-throughput social feed delivery pipeline (fan-out services, caching strategies, data aggregation, and low-latency API serving).
• Power ML & Recommendation Pipelines: Implement ranking algorithms, personalized recommendation pipelines, and content filtering using modern ML approaches (e.g., candidate generation, two-tower models, collaborative filtering).
• Integrate AI/Multimodal Tools: Leverage state-of-the-art AI tooling (vector search, vision-language models, and LLM APIs) to automatically extract metadata, tag video content, and personalize user feeds.
• AWS Cloud Performance: Manage, scale, and optimize cloud services on AWS to guarantee microsecond-to-millisecond response times under peak user loads.
• Cross-Functional Collaboration: Partner directly with the founder and mobile engineering team (React Native/Expo) to ensure seamless API integration and smooth 60fps feed rendering on the client side.

Key Requirements

• 5+ years of Senior Backend Engineering experience using Python (FastAPI, AsyncIO, PyTorch, Django, or Flask).
• Proven Domain Expertise: Direct experience building or scaling social feeds, recommendation engines, or discovery algorithms (e.g., experience from Snap, TikTok, Tinder, Meta, Pinterest, or high-scale social platforms).
• AWS Cloud Expertise: Hands-on experience with core AWS services (ECS/EKS, Lambda, ElastiCache/Redis, DynamoDB, OpenSearch, S3, SageMaker/Bedrock).
• Modern AI / Vector Tooling: Familiarity with vector databases (Pinecone, Weaviate, Qdrant, or OpenSearch Vector Search) and embedding models for semantic retrieval and recommendation.
• Data & System Architecture: Strong mastery of caching strategies (Redis/Memcached), asynchronous processing (Celery/Kafka/SQS), relational & NoSQL databases, and graph database concepts.

Bonus Points

• Background in Computer Vision / Multimodal AI integration for automated video tagging and product recognition.
• Experience with real-time analytics, event-driven architectures, or A/B testing infrastructure for feed ranking models.
• Prior experience working in fast-moving startup environments.

Work Model & Location

• Prong 1 (Preferred): Hybrid / In-Office presence at our office in El Segundo, CA (Greater Los Angeles Area).
• Prong 2 (Remote Option): Remote for exceptional social feed specialists located in North America or Latin America with strong alignment to PST work hours.