Senior Software Development Engineer I

Job Responsibilities

Job Title: Senior Software Engineer - Forward Deployed Engineering

Target Level: S5-1

Reports to: Engineering Manager, U.S. Augmented Intelligence Team

Job Location: San Diego, CA, U.S.

About SHEIN

SHEIN is a global online fashion and lifestyle retailer, offering SHEIN branded apparel and products from a global network of vendors, all at affordable prices. Headquartered in Singapore, with more than 15,000 employees operating from offices around the world, SHEIN is committed to making the beauty of fashion accessible to all, promoting its industry-leading, on-demand production methodology, for a smarter, future-ready industry.

Position Summary

SHEIN Technology is looking for a Senior Software Engineer (Forward Deployed Engineering) to join the U.S. Augmented Intelligence Team and own production AI systems that help U.S. Marketplace sellers onboard and list products at scale. You will build and continuously improve agentic systems that turn arbitrary seller data - spreadsheets, ERP exports, and storefront catalogs - into correct, publish-ready product listings, with AI-driven category, attribute, and brand mapping, automated verification, and human-in-the-loop review. You will also own AI automation that supports SHEIN''s U.S. business functions, such as people operations and accounting.

This role combines applied large-model engineering with production backend and integration work. Beyond shipping the first version, you will own the evaluation and improvement loop behind these agents: building benchmarks and eval harnesses from real seller data, using model-driven analysis of failures to iterate on plans, prompts, and mapping logic, and guarding against overfitting so gains hold up on unseen data. You will also serve as a technical point of contact for SHEIN Open Platform partners - ERPs, multichannel listing tools, and logistics providers - supporting their API integration, acceptance testing, and launch.

You will work directly with the U.S. Marketplace business team, U.S. corporate-function stakeholders, external integration partners, and SHEIN engineering counterparts in China. This is a high-ownership role: requirements often arrive as real seller files and partner questions rather than written specs, and you will be expected to take them from discovery to production and adoption.

Responsibilities

Own the design, development, and production operation of AI-powered product-listing and seller-onboarding tools - backend services, browser-extension front ends, and multi-agent workflows (e.g., planner / verifier) that turn heterogeneous seller data into verified data-mapping plans and published listings, with humans in control of high-risk decisions.

Build and maintain the evaluation system behind these agents - benchmark and blind holdout datasets from real seller data, end-to-end evals of the full publishing chain, and evidence-based model and configuration selection across accuracy, stability, latency, and cost.

Drive recursive improvement loops in which models analyze task runs, error logs, and eval failures to propose and validate changes to prompts, plans, and mapping rules - with explicit anti-overfitting audits before any change reaches production.

Build and run reliable production infrastructure: high-volume file and image processing, asynchronous task orchestration (e.g., Kafka), checkpointing, token-usage and publishing audit trails, observability, security remediation, on-call support, and documentation.

Own and extend the team''s internal AI automation platform for SHEIN''s U.S. business functions - e.g., workforce-productivity automation integrating HR and project-management systems and accounting workflow automation - from requirements and data-source changes through rollout, stakeholder onboarding, and ongoing maintenance.

Serve as a technical point of contact for SHEIN Open Platform partners (API support, UAT, acceptance, and coordination with SHEIN engineering in China), and work directly with U.S. Marketplace stakeholders and pilot sellers to prioritize features, run demos, and drive adoption from internal tool to seller-facing product.

Job Requirements

Skills and Qualifications

Master''s degree in Computer Science, Artificial Intelligence, or a related field - or equivalent practical experience - with 3+ years of professional software engineering experience, including shipping LLM-powered applications to production.

Proven track record building and evaluating production agentic systems on LLMs - multi-step tool use, structured output, multi-agent orchestration, and designing around non-deterministic behavior; ability to build eval datasets from real business data, separate training and blind holdout sets, and catch regressions when models, prompts, or data change. Experience with LangGraph / LangChain is a plus.

Proficiency in Java and Python, with hands-on experience building backend services using Spring Boot and MyBatis. Working knowledge of TypeScript/JavaScript, React and Next.js for building web front-ends and browser extensions.

Solid backend, database, and integration skills - REST APIs and webhooks, relational databases such as MySQL, caching with Redis, message queues such as Kafka, containerized deployment, high-volume data processing, and integrating with external partners and internal business systems (e.g., HR, finance, or project-management SaaS) through APIs.

Proficiency with an AI-powered coding tool (Claude Code, Codex CLI, GitHub Copilot, or Cursor) and the ability to design structured, repeatable AI-assisted development workflows.

Ability to turn ambiguous business needs and messy real-world data into reliable solutions, and to explain model behavior and limitations clearly to non-engineering stakeholders.

Preferred Qualifications

Experience with Recursive Self-Improvement (RSI) for AI agents - building closed loops in which an agent''s own runs, failures, and eval results are fed back (often through another model) to propose, test, and adopt improvements to its prompts, plans, tools, or skills, with rigor to keep them honest: blind evaluation, overfitting audits, regression gates, and human review before production.

Experience with e-commerce marketplaces and seller-side tooling - product catalogs, category taxonomies, attributes and variants (SPU/SKU), and ERP, multichannel listing, or fulfillment integrations (e.g., Shopify, Walmart, Amazon MCF, SellerCloud).

Prior experience in a forward-deployed, solutions, or technical consulting / professional-services role - embedding with business teams or external clients to scope ambiguous problems, deliver AI solutions in their production environment, and drive adoption end-to-end.

English and Mandarin bilingual fluency for collaboration with SHEIN HQ engineering teams in China.