Senior Data Engineer / AI Engineer (Agentic AI Platform – Financial Data)Location: Philadelphia, PA – Hybrid (On-site 2-3 days per week)Duration: ContractInterview Mode: VideoAbout the RoleWe are building a platform that converts unstructured financial data (emails, corporate actions, index announcements) into high-quality, structured datasets used by financial institutions.This is not a typical "LLM wrapper" role. You will work on systems that:Extract data from noisy, inconsistent sourcesValidate and reconcile outputs across multiple inputsEnsure correctness, traceability, and auditabilityThe challenge is not just applying LLMs—it's making them reliable in production for financial workflows.What You'll Work OnDesigning pipelines that process high-volume financial documents (batch + near real-time)Building LLM-powered extraction workflows (classification, parsing, summarization)Implementing validation layers (rule-based + model-based) to reduce hallucinationsDeveloping retrieval systems using embeddings and vector searchArchitecting end-to-end systems: ingestion ? processing ? storage ? servingEnsuring data quality, observability, and fault toleranceCollaborating with product to turn messy data into usable financial intelligenceCore Requirements (Must-Have)Strong Python and backend/data engineering experienceExperience building production data pipelines (ETL, streaming, or async systems)Solid understanding of distributed systems and failure modesExperience working with LLM-based systems in production including:Prompt designOutput validationRetry/fallback strategiesEvaluation and monitoringExperience with data storage systems (SQL + NoSQL)Familiarity with cloud infrastructure (AWS or similar)Preferred ExperienceExperience with RAG / vector search systemsBackground in financial data or capital marketsExperience with streaming systems (Kafka, etc.)Experience building multi-step or agent-style workflowsWhat Makes This Role InterestingWork on high-accuracy AI systems where correctness mattersSolve real problems around:LLM reliability and hallucination mitigationData consistency across conflicting sourcesReal-time vs correctness tradeoffsBuild systems used in financial decision-making workflowsHigh ownership over core architecture in an early-stage environmentNice to Know (but not required)Experience with orchestration tools (Airflow, etc.)Exposure to evaluation frameworks for LLMsExperience working with large-scale document processingTech Stack (Representative, not exhaustive)Python, APIs, async processingLLM APIs + embeddingsSQL / NoSQL databasesCloud infrastructure (AWS)Data pipelines and streaming systemsVector DatabasesNote for candidates: Local candidates only to Philadelphia, PA (no relocation accepted).