Lead GenAI Developer

Toyota North America • Plano, TX

7d

About The Position

Overview Who we are Collaborative. Respectful. A place to dream and do. These are just a few words that describe what life is like at Toyota. As one of the world’s most admired brands, Toyota is growing and leading the future of mobility through innovative, high-quality solutions designed to enhance lives and delight those we serve. We’re looking for talented team members who want to Dream. Do. Grow. with us. An important part of the Toyota family is Toyota Financial Services (TFS), the finance and insurance brand for Toyota and Lexus in North America. While TFS is a separate business entity, it is an essential part of this world-changing company- delivering on Toyota's vision to move people beyond what's possible. At TFS, you will help create best-in-class customer experience in an innovative, collaborative environment. To save time applying, Toyota does not offer sponsorship of job applicants for employment-based visas or any other work authorization for this position at this time. This position is based in Plano, TX. Who We’re Looking For: At TFS, we’re embarking on a technology transformation journey, creating next generation products and platforms. These products enable TFS to provide a best-in-class experience to our customers and partners and position us to rapidly scale to realize our vision of mobility for all by enabling freedom of movement for everyone. We are seeking a Lead GenAI Developer to design and lead cloud-native architectures on AWS that power GenAI applications and LLM-based systems. The Lead GenAI Developer will build ingestion pipelines, integrate vector databases, operate MCP servers and serverless components, and drive prompt engineering and production LLM usage. The expectation is as a Lead you will be hands-on and driving the delivery of critical business initiatives.

Requirements

• Bachelor’s Degree and/or equivalent experience.
• 6+ years cloud architecture experience, including 3+ years building production GenAI/LLM systems on AWS.
• Strong Python and AWS expertise, including Lambda, ECS/EKS, S3, SageMaker (or similar), plus Docker and Kubernetes.
• Production experience with vector databases and designing ingestion + embedding pipelines for both batch and streaming workloads.
• Hands-on with prompt design, evaluation, LLM orchestration, and RAG implementation patterns.
• Experience deploying and operating model- serving or MCP – like server infrastructure (selfhosted or managed).
• Proficient with IaC and delivery tooling, including Terraform/CloudFormation, GitOps, and CI pipelines.
• Proven skills in monitoring, logging, and automated testing for ML infrastructure and services.
• Strong communicator with clear documentation skills.

Nice To Haves

• Experience with model-serving infrastructure, such as Amazon SageMaker, NVIDIA Triton, Ray Serve, or similar platforms.
• Hands-on experience with GenAI libraries and frameworks, including LangChain, LlamaIndex, Hugging Face, and OpenAI APIs.
• Deep operational expertise with vector databases, such as Pinecone, Milvus, Weaviate, or Qdrant.
• Knowledge of data governance and regulatory compliance, including HIPAA and GDPR considerations.
• AWS Solutions Architect, AWS DevOps Engineer, or equivalent industry certifications.

Responsibilities

• Cloud Architecture & Infrastructure: Design scalable, secure AWS architectures (VPCs, IAM, networking, S3, EKS/ECS/Fargate, Lambda) and manage infrastructure using IaC (Terraform/CloudFormation), CI/CD, and observability tooling.
• LLM & GenAI Platforms: Lead integration of API-based and self-hosted LLMs, implement RAG solutions, optimize inference cost/performance, and operate MCP servers and model-serving infrastructure.
• Prompting & Evaluation: Develop prompt engineering strategies, reusable templates, and evaluation frameworks; collaborate with product teams to iterate and improve prompt quality.
• Vector Databases & Retrieval Pipelines: Implement and maintain vector stores (OpenSearch, Pinecone, Milvus, Qdrant) and design efficient similarity search, retrieval workflows, and indexing strategies.
• Data Ingestion & Processing Pipelines: Build robust ETL/ELT and document ingestion systems—batch and streaming—including data transformation, cleaning, metadata extraction, and embedding generation.
• Microservices & Serverless Systems: Develop microservices and serverless components to support low-latency inference, asynchronous processing, and event-driven architectures.
• Python Development & AI Tooling: Build core backend components in Python, leveraging LangChain, LlamaIndex, Hugging Face, and related tooling.
• Security, Governance & Cross-Functional Leadership: Enforce data privacy, secrets management, RBAC, and cost governance best practices while collaborating across teams, mentoring engineers, and maintaining operational runbooks.

Benefits

• A work environment built on teamwork, flexibility, and respect.
• Professional growth and development programs to help advance your career, as well as tuition reimbursement.
• Team Member Vehicle Purchase Discount.
• Toyota Team Member Lease Vehicle Program (if applicable).
• Comprehensive health care and wellness plans for your entire family.
• Toyota 401(k) Savings Plan featuring a company match, as well as an annual retirement contribution from Toyota regardless of whether you contribute.
• Paid holidays and paid time off.
• Referral services related to prenatal services, adoption, childcare, schools, and more.
• Tax advantaged accounts (Health Savings Account, Health Care FSA, Dependent Care FSA).

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level