Sr AI Platform Engineer - Retrieval & Knowledge Systems

This role focuses on distributed systems, retrieval architectures, and AI platform services, enabling applications and agents to discover, retrieve, and reason over large-scale enterprise data. You will work at the intersection of search, vector retrieval, LLMs, and real-time data systems, building high-performance platforms used by AI and application teams.

The ideal candidate is a strong backend/platform engineer with deep experience in building scalable systems and modern AI-powered retrieval architectures., AI Retrieval & Search Platform

• 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.

Data Pipelines & Indexing Systems

• 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.

AI Platform Services & APIs

• 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.

LLM & Intelligent Systems Integration

• 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 like AI assistants, copilots, search experiences, and automation agents.

Performance, Scalability & Reliability

• Design for low-latency (<100ms retrieval), high-throughput, and horizontal scalability.
• Implement caching, sharding, and distributed query execution strategies.
• Build observability pipelines (metrics, logs, tracing) for system performance and usage insights.
• Drive resiliency, fault tolerance, and system reliability at scale.

Technical Leadership

• Lead design and architecture of large-scale AI platform components.
• Mentor engineers on distributed systems, retrieval architectures, and AI engineering practices.
• Drive adoption of modern engineering practices (CI/CD, infrastructure-as-code, automated testing).
• Partner with AI, data, and product teams to shape next-gen intelligent platform capabilities.

What are we looking for?

We’re looking for strong collaborators who deliver exceptional client experiences and thrive in fast-paced, team-oriented environments. Our ideal candidates pursue greatness, act with integrity, and are driven to help our clients succeed. We value those who embrace creativity, continuous improvement, and contribute to a culture where we win together and create and share joy in our work.

• Minimum of 8 years of experience in backend or platform engineering.
• Experience building distributed systems, search platforms, or large-scale data services.
• Hands-on experience with APIs, microservices, and cloud-native architectures.
• Experience with search systems, indexing, or retrieval pipelines.
• Experience programming skills in Java, Python, or Go.

Preferences:

• Experience with cloud platforms and containerized environments (Kubernetes).
• Experience with Elasticsearch/OpenSearch, vector databases, or hybrid retrieval architectures.
• Familiarity with RAG systems, embeddings, and LLM integration patterns.
• Experience building AI platforms, copilots, or agent-based systems.
• Experience with real-time data systems (Kafka, streaming pipelines).
• Strong understanding of performance optimization in distributed systems.

Actual base salary varies based on factors, including but not limited to, relevant skill, prior experience, education, base salary of internal peers, demonstrated performance, and geographic location. Additionally, LPL Total Rewards package is highly competitive, designed to support your success at work, at home, and at play - such as 401K matching, health benefits, employee stock options, paid time off, volunteer time off, and more. Your recruiter will be happy to discuss all that LPL has to offer!

LPL Financial Holdings Inc. (Nasdaq: LPLA) is among the fastest growing wealth management firms in the U.S. As a leader in the financial advisor-mediated marketplace(6) , LPL supports over 32,000 financial advisors and the wealth management practices of approximately 1,100 financial institutions, servicing and custodying approximately $2.3 trillion in brokerage and advisory assets on behalf of approximately 8 million Americans. The firm provides a wide range of advisor affiliation models, investment solutions, fintech tools and practice management services, ensuring that advisors and institutions have the flexibility to choose the business model, services, and technology resources they need to run thriving businesses. For further information about LPL, please visit www.lpl.com.

At LPL, independence means that advisors and institution leaders have the freedom they deserve to choose the business model, services, and technology resources that allow them to run a thriving business. They have the flexibility to do business their way. And they have the freedom to manage their client relationships, because they know their clients best. Simply put, we take care of our advisors and institutions, so they can take care of their clients.