Responsibilities
- Design and build scalable data platforms and distributed processing systems
- Develop modern ingestion, transformation, and retrieval pipelines for structured and unstructured data
- Build systems supporting AI/LLM applications, semantic search, RAG pipelines, vector search, and agentic workflows
- Work hands-on with engineering teams to implement production-grade solutions rather than producing slideware
- Evaluate and standardize frameworks, tooling, and infrastructure patterns across teams
- Improve performance, reliability, observability, and cost efficiency of data systems
- Partner with product and platform engineering teams to accelerate delivery of AI-native capabilities
- Drive pragmatic engineering decisions balancing speed, maintainability, and operational simplicity
- Mentor engineers technically through design reviews, architecture guidance, and pair debugging
- Help establish engineering standards around CI/CD, testing, data quality, monitoring, and operational excellence
Requirements
- Significant real-world experience building and operating production systems using many of the following: Airflow, Elasticsearch / OpenSearch, Vector databases and semantic retrieval systems, MongoDB, PostgreSQL, DynamoDB, or similar platforms
- Cloud & Infrastructure: AWS, AWS CDK, Serverless architectures, Distributed observability and monitoring stacks
- AI / Search / Modern Data Applications: LLM integration patterns, RAG architectures, Embeddings and vector search, MCP servers and AI orchestration frameworks, LangChain, LlamaIndex, DSPy, or similar ecosystems, AI evaluation, tracing, and observability tooling, Search relevance and ranking systems
- Backend Engineering: Python strongly preferred, Experience with Java, Go, or TypeScript is a plus, API design and distributed service architectures, Event-driven and asynchronous systems
- Still enjoys building and debugging systems directly
- Has strong technical depth, not just architectural vocabulary
- Comfortable operating in ambiguity and fast-moving environments
- Understands how to simplify systems instead of endlessly abstracting them
- Has experience modernizing legacy platforms and evolving architectures incrementally
- Can distinguish between engineering fundamentals and hype cycles
- Values shipping working systems over theoretical perfection
Nice to Have
- Experience with large-scale news, document, or regulatory data pipelines
- Experience with search relevancy tuning and semantic retrieval
- Exposure to governance, compliance, risk, or enterprise SaaS platforms
- Familiarity with modern AI engineering workflows and agentic systems
- Experience supporting both startup-speed execution and enterprise-scale operations
