You build it, you run it. End-to-end accountability for the AI platform in production: architecture, delivery, operations, cost, and quality, with on-call for what you ship. No hand-off to a separate ops or QA function.
Design, build, and operate agentic AI systems: LLM services, retrieval pipelines, multi-agent orchestration, agent execution runtimes, and human-in-the-loop capabilities.
Build and operate memory infrastructure for agent systems (storage, retrieval, promotion/demotion mechanics). Applied Science owns promotion criteria and scientific soundness.
Own LLMOps: the harnesses, pipelines, and infrastructure that keep non-deterministic systems reliable and correct in production, including dynamic model selection by task, cost, and latency.
Build automated eval infrastructure that continuously compares offline and online metrics and alerts on drift or regression. Applied Science owns the methodology and acceptance thresholds it checks against.
- Evaluate, adopt, and integrate third-party LLMOps and eval platforms where they accelerate delivery over building in-house.
- Build the technical controls, telemetry, and guardrails that enforce compliance frameworks (e.g., ISO 42001, AIUC-1) in the architecture itself.
Build and maintain the agent definition management APIs and the tool registry definitions reference, keeping definitions stable as tools and models version independently.
Lead the engineering build of proof-of-concepts. Applied Science defines the architecture bet and validation criteria being tested.
- Core Responsibilities
- Create architecture, prototypes, and design proposals that deliver near-term business value while aligning with the future-state product and platform vision.
- Influence technical direction through architecture reviews, RFCs, design discussions, and hands-on collaboration.
- Partner with senior developers, architects, and tech leads to define and execute the product/platform architecture roadmap.
- Balance delivery speed, quality, maintainability, and long-term platform health when making technical decisions.
- Break down large initiatives into parallelizable chunks of work that deliver incremental business value.
- Champion proposals through all phases of the SDLC, from design through production implementation.
- Contribute to improving the core product build, CI/CD pipelines, and overall SDLC.
- Troubleshoot and eliminate root causes of persistent production issues; drive reliability, observability, monitoring, and incident response.
- Keep technical documentation current and create new artifacts as needed.
- Facilitate design discussions within and across teams.
- Represent the team in technical discussions with Tech Leads, Operations, Product/UX, Security, Domain SMEs, and external stakeholders.
- Act as a trusted technical leader, helping teams succeed through collaboration, influence, and shared ownership.
Mentor other developers through design reviews, joint agentic-AI sessions, and feedback on skills, prompts, and other agent inputs; contribute to raising overall engineering maturity.
- Share knowledge of new technologies and industry best practices.
- Evaluate emerging technologies, frameworks, and cloud capabilities that could benefit the platform.