Agent Platform Engineer
Job Description
Agent Platform Engineer
Company Overview
A leading artificial intelligence and advanced analytics organization is seeking an Agent Platform Engineer to help develop next-generation AI orchestration and decision-support platforms. Based in Los Angeles, California, the company specializes in integrating complex data sources into scalable intelligence solutions that support mission-critical operations, advanced analytics, and organizational workflows. This is an opportunity to work on cutting-edge AI technologies within a highly collaborative and innovative engineering environment.
Role Summary
The Agent Platform Engineer will design, build, and optimize enterprise-grade AI platforms that connect structured and unstructured data, knowledge graphs, retrieval systems, and intelligent workflows. This hands-on role focuses on developing production-ready AI applications, agent frameworks, workflow orchestration systems, retrieval pipelines, and model-serving infrastructure. The ideal candidate combines strong software engineering fundamentals with expertise in AI systems, distributed architectures, and scalable platform development.
Key Responsibilities
- Design and implement intelligent workflow systems for research, analysis, automation, and decision-support use cases.
- Develop scalable retrieval, search, and knowledge management capabilities across structured and unstructured datasets.
- Build backend services, APIs, and platform capabilities supporting AI-driven applications.
- Create resilient workflow orchestration patterns for long-running, distributed, and fault-tolerant processes.
- Develop authorization, permission management, auditing, and governance mechanisms within AI platforms.
- Optimize retrieval, inference, and execution performance across diverse deployment environments.
- Fine-tune, evaluate, and integrate open-source AI models to support specialized business workflows.
- Implement model routing, inference optimization, caching, and fallback strategies.
- Build evaluation frameworks that measure system accuracy, reliability, performance, and operational effectiveness.
- Develop observability, monitoring, alerting, and troubleshooting capabilities across platform components.
- Partner with product, data, machine learning, infrastructure, security, and customer-facing teams to deliver scalable solutions.
- Contribute to technical architecture, engineering standards, and long-term platform strategy.
Additional Details
- Fully onsite 5 days per week
- Individual contributor role with substantial technical ownership
- Opportunity to work on advanced AI, automation, retrieval, and knowledge graph technologies
- Staff-level candidates may provide technical leadership, mentorship, and architecture guidance
- Candidates must be authorized to work in the United States and satisfy applicable regulatory employment requirements
Required Qualifications
- Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related technical discipline, or equivalent practical experience.
- 5+ years of experience building and operating production software platforms and distributed systems.
- Strong Python development experience with expertise in backend services, APIs, databases, and event-driven architectures.
- Experience building AI, search, retrieval, workflow automation, or intelligent application platforms.
- Hands-on experience with workflow orchestration, long-running processes, failure recovery, and distributed execution models.
- Experience with semantic retrieval and structured data access technologies such as SQL, graph databases, or analytical query platforms.
- Experience training, fine-tuning, adapting, evaluating, or deploying modern AI models.
- Experience deploying and optimizing applications across multiple computing environments, including cloud, edge, or on-premises infrastructure.
- Strong analytical, problem-solving, and system design capabilities.
- Excellent written and verbal communication skills.
Preferred Qualifications (Nice-to-Haves)
- Experience with knowledge graphs, hybrid retrieval, entity-centric search, or data provenance systems.
- Experience with workflow orchestration platforms and durable execution frameworks.
- Familiarity with AI agent frameworks, tool orchestration, model routing, and retrieval-augmented architectures.
- Experience implementing RBAC, ABAC, multi-tenant authorization, or permission-aware data access controls.
- Experience supporting geospatial analytics, mapping systems, or spatial data platforms.
- Experience deploying AI applications within regulated, highly secure, or disconnected environments.
- Knowledge of model serving, inference optimization, GPU acceleration, caching, batching, and performance tuning.
- Experience with TypeScript, React, or modern web application technologies.
- Background in defense, public sector, public safety, intelligence, or other high-consequence operational environments.
- Proven technical leadership experience mentoring engineers and defining platform standards.
Compensation & Benefits
- $200K-$300K + discretionary bonus
- Performance-based bonus opportunities
- Comprehensive medical, dental, and vision coverage
- Retirement savings program
- Generous paid time off and company holidays
- Professional development and continuing education opportunities
- Access to cutting-edge AI technologies and large-scale engineering initiatives
