This is a fully remote position, open to applicants in United States.

📋 Description

• Development of agent orchestration frameworks to facilitate multi-step reasoning, tool usage, and constraint-based problem solving within banking workflows.

• Implementation of RAG pipelines that encompass embedding generation, chunking, hybrid retrieval, and retrieval evaluation, specifically tailored for banking document types.

• Integration layers for LLM that connect banking models, APIs, and knowledge bases, ensuring reliable and auditable inference workflows.

• Establishment of evaluation infrastructure that includes behavioral contracts, regression baselines, and production observability for non-deterministic AI outputs.

• Creation of backend services and APIs that support client-facing AI products, adhering to bank-tier uptime standards.

⛳️ Requirements

• A minimum of 5 years in software engineering, with at least 2 years focused on developing and deploying production-grade agentic AI or RAG systems.

• Experience with agent frameworks such as LangChain, LangGraph, PydanticAI, AutoGen, or Semantic Kernel.

• Proficiency in RAG stack technologies, including embedding models, vector databases (Pinecone, Weaviate, Milvus, FAISS), hybrid search, and retrieval evaluation.

• In-depth understanding of LLM integration, encompassing tool calling, structured outputs, multi-step reasoning, and behavioral regression testing.

• Familiarity with AI evaluation and observability tools, such as LangSmith, RAGAS, DeepEval, Arize, Langfuse, or similar alternatives.

• Experience with REST APIs, asynchronous Python, and microservices; Azure cloud experience is preferred.