Sr AI Platform Engineer – Retrieval & Knowledge Systems

Job Overview

The Senior Engineer will design and build core AI knowledge infrastructure that powers intelligent applications across the enterprise, focusing on distributed systems, retrieval architectures, and AI platform services. The role enables applications and agents to discover, retrieve, and reason over large‑scale enterprise data at the intersection of search, vector retrieval, LLMs, and real‑time data systems.

• Design and build high‑scale retrieval systems combining keyword search, semantic search, and vector‑based retrieval.
• Develop RAG (Retrieval‑Augmented Generation) infrastructure including indexing, retrieval, ranking, and context assembly.
• Build and optimize search indices, vector stores, and hybrid retrieval systems for relevance, latency, and scale.
• Implement advanced ranking, relevance tuning, and personalization pipelines.

• Build streaming and batch pipelines for ingesting and transforming structured and unstructured data.
• Develop enrichment pipelines (chunking, embeddings, metadata extraction, classification).
• Design systems for real‑time indexing, incremental updates, and freshness guarantees.
• Optimize data flow, storage, and compute efficiency at scale.

• Build low‑latency, highly available APIs that expose retrieval and knowledge services to applications and AI agents.
• Develop reusable SDKs and service abstractions for easy integration into product teams.
• Enable context retrieval, query understanding, and response augmentation for downstream AI systems.
• Establish patterns for multi‑tenant, scalable platform services.

• Integrate LLMs with retrieval systems to enable grounded, context‑aware experiences.
• Build systems for context construction, prompt augmentation, and response orchestration.
• Implement evaluation frameworks for relevance, grounding quality, and user experience.
• Support use cases such as AI assistants, copilots, search experiences, and automation agents.

• Design for low‑latency (