We are seeking a Senior AI / Generative AI Architect with deep hands-on experience designing and architecting enterprise-grade Agentic AI, LLM, RAG, and multi-agent platforms. The ideal candidate will provide technical leadership in building scalable AI architectures using Python, LangGraph, LangChain, CrewAI, RAG, vector databases, LLM orchestration, and cloud-native technologies.
The Architect will be responsible for defining AI platform architecture, designing agent workflows and memory systems, establishing enterprise integration patterns, and ensuring production-grade security, observability, evaluation, scalability, and reliability of AI solutions.
Key Responsibilities
- Architect and lead the design of enterprise-scale Agentic AI and Generative AI platforms using Python, LangGraph, LangChain, CrewAI, and LLM technologies.
- Define scalable architectures for single-agent and multi-agent workflows, including orchestration, routing, state management, tool/function calling, planning, and agent collaboration.
- Design enterprise-grade RAG architectures covering document ingestion, chunking, embeddings, retrieval, reranking, contextualization, and response generation.
- Architect data, memory, and knowledge layers using PostgreSQL, SQLAlchemy/Alembic, Qdrant, pgvector, and other vector/knowledge storage technologies.
- Establish architectural patterns for short-term and long-term agent memory, conversation state, session management, and persistent knowledge.
- Design and implement highly reliable FastAPI-based AI services using Pydantic, PyTest, Docker, and modern Python engineering practices.
- Architect integrations with enterprise data platforms and applications including Snowflake, Salesforce, Glean, Gong, and other business systems.
- Design secure and scalable LLM gateway, model integration, and provider abstraction layers supporting enterprise AI workloads.
- Define and implement LLM evaluation frameworks covering accuracy, groundedness, relevance, hallucination, latency, cost, safety, and agent/tool execution quality.
- Establish AI observability and monitoring architecture, including traces, metrics, logs, token usage, latency, failures, model behavior, and agent execution.
- Design and enforce AI security and responsible AI controls, including prompt-injection protection, data leakage prevention, guardrails, access control, and secure tool execution.
- Architect production deployments of AI/LLM workloads on GCP, leveraging cloud-native services, containerization, scalability, availability, and disaster-recovery practices.
- Establish CI/CD and engineering standards using GitHub, GitHub Actions, Docker, automated testing, code reviews, and deployment automation.
- Provide technical leadership and architectural guidance to AI/ML engineers and development teams.
- Define architecture standards, design patterns, reference architectures, technical documentation, and engineering best practices for enterprise AI.
- Evaluate emerging LLM, Agentic AI, RAG, MCP, vector database, and AI orchestration technologies and recommend their adoption where appropriate.
- Collaborate with product, data, security, cloud, engineering, and business teams to translate business requirements into scalable AI solutions.
- Drive AI solutions from proof of concept through production, ensuring maintainability, scalability, security, performance, and operational readiness.
Required Technical Skills
- 15+ years of overall software/technology experience with significant experience in architecture and technical leadership.
- Strong hands-on experience with Python 3.11+ and enterprise Python application development.
- Deep expertise in Generative AI, LLMs, Agentic AI, AI agents, and multi-agent architectures.
- Strong experience with:
- LangGraph
- LangChain
- CrewAI
- LLM agents and orchestration
- Tool/function calling
- Agent routing and state management
- Agent memory
- RAG architectures
- Strong knowledge of LLM application architecture, including model selection, prompting, context management, embeddings, retrieval, and inference patterns.
- Hands-on experience with PostgreSQL, SQLAlchemy, Alembic, and data persistence architectures.
- Experience with vector databases such as Qdrant and pgvector.
- Strong understanding of embeddings, chunking, semantic search, vector retrieval, hybrid search, and RAG optimization.
- Strong experience building production APIs using FastAPI and Pydantic v2.
- Experience with PyTest, automated testing, and quality engineering for AI applications.
- Strong experience with Docker and containerized deployments.
- Production experience with GCP and cloud-native AI application deployment.
- Experience with Snowflake and enterprise data integration.
- Strong understanding of GitHub and GitHub Actions, CI/CD, branching strategies, code reviews, and automated deployments.
- Experience designing LLM evaluation, observability, monitoring, and AI guardrail frameworks.
- Strong understanding of prompt injection, jailbreaks, data leakage, secure tool calling, and AI application security.