Agios AI Foundation Software Engineer

Meta•Redmond, WA

About The Position

At Meta Reality Labs Research (RL-R), our goal is to explore, innovate and design novel interfaces and hardware subsystems for the next generation of virtual, augmented, and mixed reality experiences. We are looking for a software engineer to join a team focused on AI tooling and infrastructure within RL-R. The team builds the agent frameworks, LLM tooling, and developer-facing libraries that other engineering teams use to ship AI-driven features. We are the layer between cutting-edge model capability and the engineers who turn that capability into products. You will design and build that platform: the SDKs, abstractions, evaluation harnesses, and reference patterns for agentic and LLM-powered systems running across the stack. You will work alongside researchers, AI engineers, and engineers in adjacent teams to take prototypes from "works in a notebook" to "owned, observable, and production-ready." This is a new team and an early hire, so the work is a mix of greenfield building and pattern-setting that other teams will adopt. You will have access to cutting-edge technology, resources, and testing facilities across RL-R.

Requirements

Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta
Experience translating fast-moving prototypes and research artifacts into production systems, working directly with researchers or AI partners
3+ years of software engineering experience, with a systems and Python background
Experience shipping LLM-powered or agentic features to production, not just prototypes
Experience designing developer-facing libraries, SDKs, or platforms that other engineers build on top of
Hands-on familiarity with modern LLM and agent tooling: prompt design, tool use, retrieval, structured output, evaluation

Nice To Haves

Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements)
Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)
Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies
Experience building or operating evaluation infrastructure for LLM-powered systems (offline eval, online metrics, regression detection)
Experience with agent frameworks (e.g. LangChain, LlamaIndex, AutoGen, or comparable internal stacks) and an opinion on what works at scale
Experience with LLM serving, latency optimization, or cost-aware orchestration of model calls
Experience contributing to wearables, AR/VR, or other constrained-compute product surfaces
Experience with multimodal AI features (vision, audio, sensor inputs)

Responsibilities

Design and build shared agent and LLM tooling: framework abstractions for tool use, retrieval, memory, and orchestration that other teams consume
Build evaluation infrastructure for LLM-powered features: offline eval harnesses, regression detection, prompt and model versioning, observability for agent behavior in production
Partner with product-facing teams to take AI prototypes into production-ready systems with clear quality, latency, and cost budgets
Set technical patterns and quality bars for AI work: how teams structure agents, evaluate them, ship them, and monitor them
Collaborate with researchers and AI engineers across RL-R to land new capabilities into the runtime in a way other engineers can build on
Contribute to planning, design, and code reviews across the team and adjacent groups
Experience translating fast-moving prototypes and research artifacts into production systems, working directly with researchers or AI partners