Infrastructure Optimization & AI Technical Lead
-
Software Development
Job Description & How to Apply Below
Location:
4910 Tiedeman Road, Brooklyn Ohio
The Infrastructure Optimization & AI (IOAI) organization is transforming Enterprise Technology Services (ETS) from reactive operations and manual analysis toward proactive, predictive intelligence and governed Generative AI adoption. At the heart of this mission is the Operational Digital Intelligence Platform (ODP) and its flagship conversational intelligence product family, including AskIT, Ask for Network, and AskIT for NOC. We are seeking a Technical Lead who bridges the gap between high-level enterprise architecture and hands‑on software development.
In this role, you will define and implement scalable GCP architectures while actively writing and reviewing high‑quality production code. You will serve as the technical authority across our core platform build, guiding cross‑functional engineering squads in delivering robust data pipelines, deterministic policy engines, indexing and retrieval systems, and Google Enterprise AI agentic workflows.
- Architect Scalable Cloud Solutions:
Design and implement modular, loosely coupled cloud architectures on GCP that scale independently and adhere to strict enterprise reliability and zero‑trust standards. - Enforce Design Patterns:
Establish canonical schemas, interface contracts, and reusable platform patterns across ingestion, normalization, storage, and AI reasoning layers. - Bridge Architecture & Squad Delivery:
Translate product roadmaps and Architecture Review Board (ARB) specifications into actionable engineering milestones, technical spikes, and clear interface contracts. - Mentor & Guide Squad Engineers:
Provide technical mentorship, code reviews, and architectural guidance to squad developers and partner engineering teams (including TCS engineers) across sprints.
- Backend Micro services:
Develop high‑performance, containerized micro services and jobs using Python (FastAPI, Pydantic v2) hosted on GCP Cloud Run. - Deterministic Policy Engines:
Build deterministic validation and evaluation engines that isolate critical business logic (e.g., CIDR math, precedence rules) from probabilistic LLM outputs to guarantee zero hallucinations on deterministic operations. - Canonical Data Contracts:
Implement strict schema validation and data contracts for ingesting structured and unstructured operational telemetry from systems like Git Lab, Palo Alto Panorama, Service Now, and GCP APIs. - Resilience & Idempotency:
Design idempotent pipelines, automated quarantine routing for malformed payloads, and self‑healing deployment models.
- Agentic Orchestration:
Architect conversational agent workflows using Vertex AI Agent Builder, Gemini, and agentic frameworks (e.g., Lang Graph), integrating custom tool routing, memory, and complexity routing. - Knowledge Retrieval & GraphRAG:
Implement advanced hybrid retrieval combining Spanner Graph, vector embeddings, and Vertex AI Search to power grounded, multi‑hop operational reasoning. - Grounding & Provenance:
Enforce 100% evidence provenance, ensuring all AI‑generated responses carry verifiable citations linking back to authoritative rule IDs, commit hashes, or documentation. - AI Evaluation & Safety Gates:
Partner with QA and AI Assurance teams to implement evaluation pipelines (using frameworks like Braintrust) to measure grounding, latency, and enforce safety gates (e.g., zero False ALLOWs on golden corpora).
- Zero‑Touch CI/CD:
Implement automated testing, container scanning, and zero‑touch deployment pipelines to ensure repeatable, immutable cloud releases. - Security & Access…
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).
View / Apply for Jobs
Matching My Jurisdiction