Lead AI Architect & Delivery Manager

New
J
JobgetherEnterprise AI
Based in the United StatesFull-TimeLead
Salary not disclosed
Apply NowOpens the employer's application page

Job Details

Experience
At least 2 years of direct, hands-on experience building, deploying, and debugging autonomous multi-agent systems in production environments.
Required Skills
PythonFastAPIDistributed Systems

Requirements

  • Have strong professional experience developing production-grade applications with Python.
  • Bring deep expertise in asynchronous programming with Asyncio, FastAPI, software design patterns, and distributed systems.
  • Have at least 2 years of direct, hands-on experience building, deploying, and debugging autonomous multi-agent systems in production.
  • Have practical experience with agentic AI frameworks such as LangGraph, AutoGen, CrewAI, or LlamaIndex.
  • Be able to design function-calling workflows and structured output pipelines connecting LLMs with traditional software APIs.
  • Have experience with structured data validation and generation tools such as Pydantic, Instructor, or native function schemas.
  • Have hands-on experience with vector databases and relational storage, including PostgreSQL/pgvector, Pinecone, Qdrant, Milvus, or Oracle 23ai.
  • Understand RAG architectures and enterprise AI application development.
  • Have experience designing unit tests, integration tests, and regression evaluations for probabilistic and LLM-driven applications.
  • Be able to evaluate AI system performance, troubleshoot technical issues, and ensure production reliability.
  • Bring communication and stakeholder-management skills for working with technical teams, business leaders, and information security specialists.
  • Have experience coordinating engineering teams and managing Agile delivery, sprint planning, and project milestones.

Responsibilities

  • Own the end-to-end architecture of the Snowflake Cortex RAG pipeline, aligned with enterprise TPRM standards.
  • Define the AI solution's technical strategy for scalability, reliability, security, and business requirements.
  • Serve as the primary technical liaison between engineering teams and client stakeholders.
  • Lead UAT sessions with InfoSec specialists and translate findings into prioritized engineering backlog items.
  • Coordinate the offshore engineering team to implement improvements and resolve issues.
  • Oversee AI governance and compliance activities, including preparation of the Model Development Documentation package.
  • Drive the AIEC-2 Effective Challenge Tier 2 clearance process ahead of production deployment.
  • Lead daily Agile stand-ups, sprint planning, and delivery coordination for a three-person offshore team.
  • Track project progress, dependencies, risks, blockers, milestones, budget, and timeline.
View Full Description & ApplyYou'll be redirected to the employer's site
View details
Apply Now