Technical Lead, AI Engineering (Sales, Service & Supply Chain)

Lucid Motors•Newark, NJ

15d

About The Position

Lucid is implementing an AI layer across its commercial and industrial operations, encompassing sales, service, and supply chain management. This role is pivotal in setting the technical direction for this initiative and ensuring its successful transition into production. The position requires close collaboration with business stakeholders, identifying problems, designing solutions, contributing to development, and leading a distributed engineering team. This is a hands-on technical leadership role focused on architecture and coding, not a management track.

Requirements

10+ years of experience building and operating production software.
3+ years of experience owning the technical direction of a team or a significant platform.
Strong Python skills and solid distributed systems fundamentals.
Comfortable owning services end-to-end, including post-deployment operations.
Real-world production experience with LLM applications, including retrieval-augmented generation, agent and tool-calling patterns, structured output, streaming, and prompt design/iteration under load.
Strong hands-on experience with LLM engineering tooling like Langfuse or LangSmith for tracing, prompt versioning, evaluation, and production monitoring.
Good working experience with MCP: building and consuming MCP servers, designing tool schemas, and handling authentication/permissions at the tool boundary.
Practical command of LLM cost optimization techniques (model routing, context compression, caching, batching, token budgeting).
Experience delivering AI over customer and employee communication channels (chat, email, SMS) and their integrations.
Sound judgment on the LLM landscape (hosted models, managed services, fine-tuning) to make defensible choices on cost, latency, and accuracy.
Strong AWS engineering experience (or equivalent), including serverless and container workloads, event-driven design, IAM, networking basics, and cost awareness at scale.
Experience with the data layer behind AI systems (relational, document, vector) and maintaining retrieval accuracy.
A concrete point of view on evaluating AI systems and the discipline to build robust evaluation harnesses.
Experience working with non-technical stakeholders and translating business intent into system design.

Nice To Haves

Background in automotive, manufacturing, logistics, or another operations-heavy domain.
Exposure to SAP, supply chain execution, EDI, or field service and CRM platforms.
Hands-on work with messaging and contact center platforms (e.g., Twilio, Amazon SES/Pinpoint, Salesforce Service Cloud).
Experience with security-sensitive AI work (prompt injection defense, data isolation, red-teaming).
Multi-agent orchestration or experience running a large-scale evaluation program.
Experience leading distributed teams across US and India time zones.

Responsibilities

Own the architecture for LLM-based and agentic systems across Sales, Service, and Supply Chain, including assistants over enterprise knowledge, agents acting against internal APIs, document and data extraction pipelines, and shared platform components.
Deliver these systems through existing customer and employee communication channels such as web and in-app chat, email, and SMS.
Manage the conversational contract across channels, ensuring continuity of context, seamless handoffs to human agents, and appropriate tone.
Translate business problems into engineering plans, working with stakeholders to define outcomes and sequence work for early and continuous value delivery.
Develop mechanisms to ensure AI safety in the enterprise, including input/output guardrails, identity-aware access to tools and data, prompt governance, and clear trust boundaries.
Own the tool layer, including MCP servers and internal tool interfaces, ensuring agents interact with business systems through versioned, permissioned, and testable contracts.
Define quality measurement standards, including evaluation datasets, regression suites, tracing, and production telemetry, and enforce them as gates for prompt and model changes.
Manage unit economics, setting and achieving targets for cost and latency per conversation and resolution through techniques like model routing, context trimming, caching, and batching.
Integrate with systems of record such as ERP, supplier portals, service and CRM platforms, and logistics and planning systems.
Set standards for the wider team, including shared services, reusable patterns, and review expectations, ensuring their effectiveness beyond personal code.
Provide technical leadership across time zones, collaborating closely with the engineering team in India.
Mentor engineers, review designs, and serve as a primary resource for complex technical challenges.
Provide honest assessments of AI's applicability, helping to prevent costly detours.