Senior AI Engineer

About the Job

We're looking for an AI-first Senior Engineer to help move our team from light AI use to agent-driven, multi-agent development. You'll build AI-powered product features end to end, work agent-first in your own day-to-day development, and share what works so the rest of the team can follow. You're also a strong full-stack engineer with modern stack experience, ready to play a key role in an upcoming ground-up rebuild (v2) of our platform while keeping our existing Java/Oracle platform running in the meantime. AI-first development: Be a hands-on early adopter: try agentic and multi-agent development workflows on real work, and find what works for our codebase and team. Share what you learn by demonstrating workflows, contributing best practices and documentation, and helping teammates get up to speed. Apply AI across the development lifecycle, from coding and testing to code review, CI/CD, and work on our legacy codebase and platform migration. AI product engineering: Design, build, and ship AI-powered product features end to end, such as LLM-based assistants and chatbots, summarization, translation, classification, predictive analytics, personalization, anomaly detection, and intelligent automation. Build LLM applications and agents using prompt engineering, retrieval-augmented generation (RAG), tool/function calling, structured outputs, and multi-step agentic workflows. Evaluate, select, and integrate AI models, APIs, and frameworks into our applications and internal tooling, balancing quality, latency, and cost for each use case. Set up evaluation and quality practices for AI features: test datasets, automated evals, regression testing of prompts and models, and production monitoring for accuracy, latency, and cost. Make AI features safe and reliable with guardrails, data privacy and PII handling, prompt-injection mitigation, and sensible fallback behavior. Partner with product teams to identify customer-facing use cases where AI can drive measurable value and competitive advantage, and rapidly prototype to validate them. Stay current with the fast-moving AI landscape (models, tools, and techniques) and bring practical improvements into the product and the team. Full-stack engineering: Play a key role in a ground-up rebuild (v2) of our platform on a modern stack, designed from the start for AI-first development. Maintain and enhance our existing platform (JSP, Java Spring, Oracle Database, PL/SQL) through the transition and help plan and execute the migration to v2. Design and implement robust, scalable, and secure web applications. Collaborate with cross-functional teams to define, design, and implement new features. Ensure the performance, quality, and responsiveness of applications. Identify and resolve bottlenecks and bugs. Help maintain code quality, organization, and automation. Participate in code reviews. Implement and manage continuous integration and continuous delivery (CI/CD) pipelines, including for AI-powered services. AI engineering: Proven experience designing, building, and deploying AI/LLM-powered features to production (e.g., chatbots and assistants, summarization, recommendation engines, predictive analytics, personalization). Hands-on experience with LLM APIs and platforms (e.g., OpenAI, Anthropic, AWS Bedrock, AWS SageMaker), including prompt engineering, tool/function calling, and structured outputs. Experience building retrieval-augmented generation (RAG) pipelines, including embeddings, chunking, and vector search (e.g., pgvector, OpenSearch, Oracle AI Vector Search). Familiarity with AI orchestration and agent frameworks (e.g.

Nice to Have

(Bonus) Proficiency in Python for AI/ML work. (Bonus) Grounding in ML fundamentals, or experience fine-tuning models. (Bonus) Experience leading or contributing to a major platform rebuild or legacy-to-modern migration. (Bonus) Experience in mobile app development (e.g., React Native, Swift/iOS, Kotlin/Android). (Bonus) Familiarity with UI/UX design, including designing intuitive user experiences for AI features.

Desired Candidate Profile

Proven experience designing, building, and deploying AI/LLM-powered features to production (e.g., chatbots and assistants, summarization, recommendation engines, predictive analytics, personalization). Hands-on experience with LLM APIs and platforms (e.g., OpenAI, Anthropic, AWS Bedrock, AWS SageMaker), including prompt engineering, tool/function calling, and structured outputs. Experience building retrieval-augmented generation (RAG) pipelines, including embeddings, chunking, and vector search (e.g., pgvector, OpenSearch, Oracle AI Vector Search). Familiarity with AI orchestration and agent frameworks (e.g.

Nice to Have