Member of Technical Staff - Agent Platform (Agent OS)

About Boson AI: At Boson AI, we are not just building AI solutions; we are pioneering the future of enterprise AI. Driven by a passion for cutting-edge AI research, particularly in the transformative areas of large language models and agentic systems, our mission is to tackle the most complex real-world problems for businesses and unlock significant value. We are a dynamic and collaborative team of researchers and engineers who thrive on pushing the boundaries of what's possible, dedicated to delivering high-quality, reliable products that seamlessly integrate into the fabric of enterprise workflows and set new industry standards. About the Role: Engineer and evolve the core Agent OS—a high-performance, resilient platform encompassing the dialog & policy engine, distributed context & memory, execution runtime, security isolation, voice runtime, and complex agentic orchestration frameworks. This system underpins all Boson agents, from low-code configuration flows in Workspace to advanced, production-grade systems leveraging RAG, ReAct, robust tool calling, and multi-step execution.

Responsibilities

System Ownership: take ownership of the core dialog & policy engine, including state machine, decision-making logic, and safety policy enforcement at the execution layer; Distributed Context & Memory: design, implement, and maintain high-performance context and memory systems, including RAG and vector retrieval pipelines; Agentic Orchestration Frameworks: define, architect, and deliver orchestration patterns such as planner–executor schemes, ReAct-style loops, and resilient multi-step workflows; Internal SDK/Framework Development: build production-grade internal frameworks with composable graphs, execution chains, clear APIs, and type safety; Voice Runtime Infrastructure: own and optimize voice runtime components for streaming audio, low-latency barge-in detection, and turn-taking protocols; Tooling & Integration Architecture: architect secure tooling and integration frameworks (MCP/A2A), including tool registration, authentication/authorization, rate limiting, circuit breaking, retries, and typed I/O; Platform Observability & Reliability: define and monitor SLIs/SLOs, improve reliability, debuggability, and performance; API & Abstraction Design: ensure public-facing APIs and internal abstractions are clear, documented, and sound; Advanced Capabilities R&D: prototype future capabilities such as on-device personalization, privacy-preserving federated learning signals, and policy adaptation techniques

Requirements

3+ years of hands-on experience in backend engineering and distributed systems, with a track record of building and owning core platforms or frameworks used by other engineering teams; Demonstrated, hands-on experience architecting, building, or operating production-grade agentic systems, including orchestrating LLM calls, managing complex tool interactions, and defining stateful workflows; Strong working knowledge of engineering orchestration frameworks (e.g., LangChain, LlamaIndex, or internal equivalents) and understanding of design patterns such as RAG, ReAct, and multi-step planning; Deep and practical understanding of distributed system design, concurrent programming, and building for reliability in multi-tenant cloud environments with strictly defined latency and cost envelopes; Proven experience designing, implementing, and rolling out frameworks or libraries that other internal engineering teams adopt; Comfort and prior experience with security-sensitive systems, including authz/authn schemes, isolation boundaries, data protection protocols, and integration with centralized policy/safety infrastructure; Strong technical communication skills and ability to lead complex, cross-functional technical initiatives

Nice to have

Experience developing and operating conversational AI platforms, agent frameworks, or high-throughput, complex workflow engines in a production setting; Engineering background in real-time media (audio/video) systems or low-level signaling protocols where extreme low-latency and jitter management are critical; Prior experience building high-stakes enterprise platforms (e.g., payments, identity, core data services) where correctness, auditability, and reliability are non-negotiable; Exposure to federated learning models, on-device personalization, or bandit-style adaptive policy systems