Staff Engineer, AI & Business Operations

Faraday Future•El Segundo, CA

21h

About The Position

As Staff Engineer, AI & Business Operations, you will be responsible for building an enterprise-grade AI Agent platform that elevates large model capabilities from an “information generation tool” to “executable business productivity,” driving AI to play a deep role in the company’s core business processes and operational decision-making. You will lead the design and implementation of an enterprise-level Agent system similar to OpenClaw, connecting AI models, enterprise data, and business systems to deliver an end-to-end closed loop: task understanding → data retrieval → decision generation → automated execution. The platform will serve sales and commercial systems and gradually expand to enterprise operations and management scenarios.

Requirements

Bachelor’s degree or above in Computer Science or a related field.
7+ years of software engineering experience, including 2–3 years of experience with AI/LLM/Agent systems.
Strong backend engineering skills with proficiency in Python (core), or Java / Node.js.
Hands-on experience building AI Agent / automated execution systems (tool calling, multi-step tasks, workflows).
Familiarity with RAG, vector databases, retrieval, and reranking mechanisms.
Experience with API design, system integration, and distributed architecture.
Cloud-native experience with AWS/GCP, Docker, and Kubernetes.
Familiarity with OAuth2/OIDC, access control, and security-by-design principles.
Ability to translate business problems into AI solutions.
Strong cross-functional communication and influence skills.

Nice To Haves

Experience with OpenClaw or similar Agent / automated execution frameworks.
Experience building enterprise-grade AI platforms or internal tooling platforms.
Experience with CRM, ERP, RevOps, or commercial systems.
Experience combining AI with data platforms or BI systems.
Familiarity with multi-Agent collaboration and complex workflow orchestration.
Proven track record of using AI to drive measurable improvements in business KPIs.
Experience leading enterprise AI transformation or scaling AI deployments.
Experience with IT / infrastructure automation (API / SSH / network devices).

Responsibilities

Design and implement an enterprise-grade AI Agent platform (Agent Runtime) supporting task understanding, planning, multi-step execution, and state management (memory).
Build a unified Tools Layer that encapsulates enterprise APIs, data services, and operational capabilities, enabling Agents to securely invoke CRM, ERP, data platforms, and other systems.
Design multi-Agent and multi-step collaboration mechanisms to support automated execution of complex business workflows.
Build cross-system task orchestration capabilities to achieve a closed loop from AI-driven insights to business execution.
Design secure and controllable execution mechanisms including approval nodes, human-in-the-loop collaboration, and rollback strategies.
Drive AI automation in business processes such as customer follow-up, task generation, data updates, and process triggering.
Build AI Copilot and Agent capabilities to support sales operations, lead management, and customer engagement.
Integrate with CRM, CPQ, order management, and customer service systems to achieve deep fusion of AI and business processes.
Collaborate with management and operational teams to identify AI application scenarios in revenue growth, conversion optimization, customer operations, cost control, and risk management.
Build a Decision Copilot for leadership to support data-driven decision-making.
Connect data platforms and AI systems to enable the flow: Data → Insights → Decisions → Execution (via Agent automation).
Establish a quantitative evaluation system linking AI outcomes to business KPIs such as revenue, conversion rates, and efficiency gains.
Build an enterprise-grade Retrieval-Augmented Generation (RAG) system integrating knowledge bases, business data, and real-time information.
Support permission-aware retrieval, citation tracing, result explanation, and temporal sensitivity controls.
Optimize embeddings, indexing strategies, reranking, and caching mechanisms to improve accuracy and performance.
Design security and governance mechanisms for AI systems, including execution tiering (read-only / low-risk / high-risk operations).
Build a comprehensive audit and compliance framework to make AI behavior traceable and explainable.
Establish a production-grade evaluation system (offline + online), A/B testing, and continuous optimization processes.
Build AI system observability capabilities including logging, tracing, and metrics.
Monitor model calls, tool execution paths, latency, and costs.
Drive platform engineering efforts to standardize and scale AI capabilities across the organization.
Lead system architecture design and key technical decisions.
Drive AI capabilities from PoC to organization-wide scaled deployment.
Guide engineering teams on best practices in Agent development, automation, and AI applications.
Bridge technology and business to advance the AI strategy.