[Remote] Senior Backend Engineer- AI Agents (Remote)

Note: The job is a remote job and is open to candidates in USA. Level AI is on a mission to turn every customer interaction into a strategic advantage through their AI-native platform. As a Senior Backend Engineer - AI Agents, you will be responsible for building scalable backend systems that power next-generation AI Agents, focusing on real-time, high-volume enterprise environments.ResponsibilitiesDesign and build scalable backend systems powering AI Agents that operate in real-time enterprise environmentsDevelop agent orchestration frameworks (multi-step reasoning, tool usage, decisioning workflows)Build systems for agent memory, context management, and state persistence across interactionsArchitect low-latency inference pipelines integrating LLMs, SLMs, and external tools/servicesImplement evaluation (evals) frameworks to measure agent performance, accuracy, and reliabilityEnable continuous improvement loops (feedback → retraining → deployment) for AI agents in productionDesign and manage event-driven, asynchronous workflows for complex agent tasksOptimize systems for high throughput, low latency, and cost-efficient inference at scaleBuild and maintain robust APIs and service layers (REST / gRPC) for agent capabilitiesPartner closely with Applied AI / ML teams to productionize models and agent behavioursCollaborate with Product and Solutions teams to translate real customer workflows into agentic systemsDrive best practices in observability, monitoring, safety, and guardrails for AI systemsContribute to architecture decisions for scaling multi-tenant, enterprise-grade AI platformsSkills5+ years of experience in backend engineering, distributed systems, or platform engineeringStrong experience building high-scale, production-grade backend systemsExperience designing systems for real-time processing, streaming, or event-driven architecturesStrong understanding of API design (REST, gRPC) and microservices architecturesExperience with databases (SQL + NoSQL) and data modeling for high-scale systemsHands-on experience with Docker, Kubernetes, and cloud platforms (AWS/GCP/Azure)Strong fundamentals in system design, concurrency, and performance optimizationExperience working with LLMs, conversational AI, or AI-powered products in productionFamiliarity with agent frameworks, tool calling, or multi-step reasoning systemsExperience building or integrating RAG pipelines, vector databases, or retrieval systemsExposure to evaluation systems (offline/online evals, A/B testing for AI systems)Understanding of prompting strategies, context windows, and model behavior optimizationExperience with real-time decisioning systems or workflow orchestration enginesBenefitsCompetitive compensation with performance-based upsideFlexible vacation policyHealth insurance coverageWork with a globally distributed, high-impact teamOpportunity to build cutting-edge AI products at scaleRegular team offsites and in-person collaborationCompany OverviewLevel AI is a platform for businesses to automate tedious workflows and transform customer experience. It was founded in 2019, and is headquartered in Mountain View, California, USA, with a workforce of 51-200 employees. Its website is https://thelevel.ai.Company H1B SponsorshipLevel AI has a track record of offering H1B sponsorships, with 1 in 2026, 2 in 2023, 1 in 2022, 1 in 2020. Please note that this does not guarantee sponsorship for this specific role.