Sr. AI Engineer, Product Development

What you’ll do

• Partner with senior technical staff to design, orchestrate, and operationalize agentic AI workflows and LLM-powered systems for tasks like documentation auditing, requirement generation, and technical knowledge retrieval.
• Build, validate, and maintain ETL pipelines and data structures that supply high-fidelity context to AI applications across siloed engineering systems, including knowledge graphs and vector databases.
• Run rapid technical trials to evaluate emerging AI approaches, moving concepts from initial trials to functional prototypes and determining which methods can reduce engineering labor.
• Convert early-stage prototypes into robust, high-performance, and scalable enterprise-grade systems.
• Define and monitor quantitative performance requirements, including accuracy, grounding, latency, and cost, to meet safety and reliability expectations in vehicle engineering.
• Work with cross-functional partners to identify manual engineering workflows and implement AI-driven automations that improve product development efficiency and productivity.

What you bring

• Bachelor’s, master’s, or PhD in a quantitative field such as Computer Science, Electrical Engineering, Mechanical Engineering, Materials Science, Physics, Mathematics, or a related discipline.
• Ideally 4-6+ years building production data pipelines and developing AI/ML solutions, with LLM-based application experience preferred.
• Strong experience in repository context engineering, AI-native IDEs & terminals, agentic loop optimization, and AI coding quality with technical debt mitigation.
• Hands-on or deep academic exposure to LLM orchestration and application concepts, including RAG (Retrieval-Augmented Generation), agentic frameworks, context engineering, grounding, evaluation, and cost/latency optimization.
• Deep understanding of how AI systems can fail differently than traditional software, including ability to create statistical validation tests, set tolerance thresholds, and track output distributions.
• Demonstrated experience with Git, eval-driven CI/CD pipelines, probabilistic validation, deployment, and end-to-end system ownership in production environments.
• Experience with high-throughput storage systems, containerized harness orchestration, and security and sandbox environments.
• Ability to extract, clean, and structure data from technical documents, requirements, or engineering specifications.
• Prior experience with physical engineering systems such as Hardware, IoT, or Telemetry.
• Strong problem-solving skills focused on product development.
• Excellent written and verbal communication skills for cross-team coordination and cross-functional leadership.
• Drive to learn and master new technologies and techniques.

Technologies you may work with

• LLM, RAG (Retrieval-Augmented Generation)
• ETL, knowledge graphs, vector databases
• Git, CI/CD, containerized harness orchestration
• Neo4j, Pinecone, Spark, Databricks
• GCP, DBT

Nice to have

• Exposure to graph technologies (e.g., Neo4j, knowledge graphs) or vector databases (e.g., Pinecone).
• Knowledge of advanced statistical techniques and concepts (e.g., regression, distribution properties, statistical tests).
• Knowledge of a variety of machine learning techniques (clustering, tree-based methods, deep learning) and their real-world tradeoffs.
• Experience building user-facing applications.
• Experience with distributed data and computing tools such as Spark, Databricks, and GCP.
• Experience with DBT.
• Passion for electric vehicles, renewable energy, and sustainable transportation.