Job Duties
Design, develop, and maintain backend services and APIs primarily in Python, supporting Genspark's AI-native super-agent platform.
Design and develop full-stack product features, including user-facing interfaces using modern web frameworks.
Build and maintain integrations with machine learning models, including Large Language Models (LLMs), to support AI-powered platform capabilities such as AI agents, conversational assistants, and content generation.
Contribute to the design and implementation of multi-agent AI systems, including orchestration of multiple ML model calls, state management across stateless model APIs, and building data pipelines for model training and prompt-engineering refinement.
Conduct machine learning model evaluation and benchmarking to compare candidate models on quality, latency, cost, and reliability metrics, informing model selection and integration decisions for production AI features.
Design and implement payment, enterprise billing, and customer-service workflows supported by AI agent systems.
Design and implement database schemas and data access patterns supporting platform features.
Collaborate cross-functionally with engineering, product, design, and go-to-market (GTM) teams to define, build, and deliver AI-enhanced production features within iterative development cycles.
Drive continuous improvement through performance optimization and AI-native development practices, including profiling, code review, and testing.
Show the full description
Job Requirements
Require Master's degree or foreign equivalent degree in Computer Science, Computer Engineering, or closely related fields.
Require two (2) years of experience in backend development and AI/ML system integration.
The experience shall include
Backend software engineering using C++ and Python;
Designing and implementing multi-agent AI systems integrated with machine learning models, including Large Language Models (LLMs);
API design and state management for real-time, latency-sensitive applications;
Building data pipelines for model training and prompt-engineering refinement;
Machine learning model evaluation and benchmarking, including comparing candidate models across quality, latency, and reliability metrics;
Tuning LLM inference parameters and refining prompts to balance output quality, latency, and cost in production;
User interface (UI) design and implementation with modern web-based UI frameworks.
Version control systems such as Git and Perforce, and with standard engineering workflows.
Annual Salary: $187,075 – $190,000
Job Location: Palo Alto, CA (On-site)