Employ is transforming how hiring gets done with innovative ATS solutions and AI technology. The Sr. Product Engineer, AI Systems will lead the architecture and evolution of AI-powered systems, ensuring reliable product capabilities and defining architectural standards for AI-driven features.
Responsibilities:
- Architect & Ship AI-Native Systems
- Lead the architecture and delivery of end-to-end AI-powered systems, including agents, RAG pipelines, orchestration layers, and reasoning workflows. Translate product vision into scalable technical systems. Define contracts, state management strategies, and guardrails for AI-driven workflows. Own and evolve API contracts that AI systems interact with, ensuring reliability, idempotency, authentication safety, and rate limiting
- Engineer Reliability at Scale
- Design schema enforcement and validation layers for AI-generated outputs. Implement retries, fallback strategies, and failure-mode containment. Establish evaluation frameworks for benchmarking, regression testing, and drift detection. Create observability standards for AI systems, including structured logging, telemetry, tracing, and performance monitoring. Productionize experimental AI capabilities into scalable, secure services
- Set Direction & Elevate the Organization
- Establish architectural patterns and standards adopted across teams. Mentor engineers in AI-native and spec-driven development practices. Influence engineering culture through clarity, urgency, and execution. Decompose high-level business outcomes into executable technical systems
Requirements:
- 4+ years building AI-augmented product capabilities (LLMs, RAG systems, agents, orchestration frameworks)
- Experience designing decoupled systems using queues such as Kafka, SQS, or BullMQ, and implementing asynchronous workflows that prevent blocking operations in user-facing systems
- Experience persisting state across sessions, managing context windows efficiently, and handling concurrency and race conditions when multiple agents interact with shared data
- Experience enforcing structured outputs using schema validation tools such as Pydantic, Zod, or JSON Schema to ensure AI-generated outputs are reliable and machine-readable
- Strong understanding of REST, GraphQL, or RPC interface design, along with authentication, rate limiting, and idempotent API patterns
- Languages: Python, including asyncio, decorators, and the modern Python ecosystem
- TypeScript / Node for integration and application-layer logic
- AI Stack: Orchestration frameworks such as LangChain, LangGraph, or custom agent loops
- Retrieval-Augmented Generation (RAG) systems
- Hybrid search, re-ranking, and chunking strategies
- Vector databases such as Pinecone, pgvector, or Weaviate
- Advanced SQL skills including query optimization and indexing strategies
- Containerization using Docker, Kubernetes or similar orchestration platforms
- Experience running isolated environments for code execution