Note: The job is a remote job and is open to candidates in USA. Commerce is an open, AI-driven commerce ecosystem and the parent company of BigCommerce, Feedonomics, and Makeswift, helping businesses solve complex commerce challenges through connected tools, systems, and data. The Lead Software Engineer - AI will define the architectural direction for AI services, build production-grade Go and LLM-based systems, establish engineering standards, and mentor senior engineers while partnering with Product and Engineering leadership.
Responsibilities
- Define and evolve the architectural direction for AI services and initiatives
- Lead high-level and low-level design for major AI programs
- Establish architectural patterns and technical guidelines that other engineers follow
- Build and evolve scalable, API-driven AI services in Go
- Develop LLM-based solutions, including classification, extraction, structured generation, and RAG workflows
- Drive rapid experimentation and prototyping (often in Python), ensuring clear paths to production-ready implementations
- Define and enforce standards for evaluation, cost-awareness, and operational reliability across AI systems
- Mentor Senior AI Engineers through design reviews and technical guidance
- Collaborate with Staff Engineers when broader architectural alignment is required
- Work directly with Product Managers and stakeholders to clarify goals and define measurable success criteria
- Balance hands-on engineering with architectural oversight
- Ensure architectural consistency and adherence to established design standards
- Raise the technical bar through thoughtful reviews and shared engineering standards
Skills
- 7+ years of professional software engineering experience
- Strong proficiency in Go (GoLang) and experience building production-grade, API-driven services
- Proficiency in Python for experimentation, prototyping, and scripting
- 3+ years of experience building and deploying AI/ML systems in production environments
- Strong experience with modern LLM ecosystems (e.g., OpenAI, Anthropic, Hugging Face)
- Deep understanding of LLM-based solution patterns, including Retrieval-Augmented Generation (RAG), structured outputs, schema-driven generation, and agents/orchestration workflows
- Familiarity with MCP (Model Context Protocol) servers and orchestration approaches
- Experience evaluating LLM performance in production contexts, including prompt design, quality measurement, and model comparison
- Experience designing and operating scalable API services at scale
- Strong experience with cloud infrastructure (AWS, GCP, or Azure)
- Experience with vector databases and inference systems
- Strong SQL skills and familiarity with modern data storage technologies
- Experience working with large taxonomies or structured classification systems
- Experience in e-commerce, product catalogs, or sales channel data models
- Familiarity with frontend frameworks (React, Angular)
Benefits
- Where applicable, this role may also be eligible for variable compensation (such as bonus or commission), equity, and benefits in accordance with local policies.
Company Overview
Company H1B Sponsorship