Tech Lead / Lead Architect – RAG & Agentic AI
I8IS INC. · Philadelphia, US
Job description
Job Summary
We are seeking an enterprise-caliber Tech Lead / Lead Architect – RAG & Agentic AI to spearhead the architecture, design, and production delivery of our next-generation cognitive systems. In this highly visible role, you will partner directly with clients and internal cross-functional squads to build scalable, secure, and exceptionally high-impact AI ecosystems.
The ideal candidate bridges the gap between deep generative AI engineering (RAG, Vector DBs, Multi-Agent Orchestration) and robust, cloud-native enterprise design.
Crucial Domain Requirement: This role sits within a highly regulated tier-1 environment. Strong financial and banking domain experience is strictly required. -
Key Responsibilities
-
End-to-End AI Architecture: Own the architecture, technical blueprint, and execution of production-grade Retrieval-Augmented Generation (RAG) and Agentic AI applications.
-
Rapid Prototyping: Build, test, and validate comprehensive Proof of Concepts (PoCs) to demonstrate technical viability before committing solutions to enterprise clients.
-
Cloud & Security Governance: Design resilient AWS infrastructures ensuring strict data privacy, enterprise network isolation, and robust AI guardrails (toxicity filtering, data leakage mitigation, and hallucination controls).
-
API & System Integration: Architect low-latency REST/GraphQL APIs, distributed microservices, and event-driven data streaming layers built specifically to power AI engines.
-
Production Optimization: Drive continuous model evaluation, operational observability, fine-tuning, latency minimization, and strict cost optimization across live models.
-
Technical Leadership: Lead from the front by mentoring developer squads, running rigorous code/architecture reviews, and maintaining delivery velocity under tight timelines.
Required Technical Matrix & Skills
Core AI Engineering (Must-Have):
-
Production experience with advanced RAG pipelines, custom embedding strategies, Vector Databases, LLM orchestration, and advanced prompt engineering.
-
Proven track record implementing AI Guardrails (toxicity, hallucination control, alignment) and managing model evaluation/observability frameworks.
Cloud Infrastructure & DevOps:
- Deep, hands-on architectural expertise within Amazon Web Services (AWS), specifically utilizing AWS Bedrock, Lambda, API Gateway, OpenSearch, S3, IAM, VPC, and Secrets Manager.
Enterprise Architecture & Integration:
- Expertise in microservices design, API modeling, and handling event-driven patterns for high-throughput AI workloads.
Preferred Qualifications (Assets)
-
Practical experience working with Agentic AI frameworks (e.g., LangGraph, CrewAI, AutoGen, Semantic Kernel).
-
Experience with multi-agent orchestration, Model Context Protocol (MCP) tool usage, and human-in-the-loop workflows.
-
Exposure to financial marketing use cases (predictive campaign optimization, hyper-personalization, analytics, and intelligence insights).
Work Environment & Interview Expectations
-
Work Arrangement: Hybrid structure requiring a mandatory 3 days per week onsite at either our Columbus, OH or Wilmington, DE corporate offices.
-
Communication: Exceptional communication skills are required. You must possess the ability to effortlessly break down complex architectural trade-offs, financial data boundaries, and risk metrics to non-technical executive stakeholders.
ML/AI Work links you to the employer's original posting — always verify the details there before applying.
More Architecture and Leadership roles
View all →Forward Deployed Engineer II
— · San Jose, US
Forward Deployed Engineer – Audit & Assurance Technology
KPMG · Remote · Basel
Forward Deployed Engineer - Clearance Required
LMI · Remote · Honolulu
Forward-Deployed AI Engineer for Federal Deployments
LMI · Baltimore, US
Founding Forward Deployed Engineer
CLERA · San Francisco, US
Forward Deployed Engineer
Wide and Wise · Southend-on-Sea, GB