Role Overview:

We are seeking a highly skilled and forward-thinking Senior Generative AI Architect to design, build, and scale our next-generation Agentic AI systems. In this role, you will transition beyond standard linear chatbots to architect complex, multi-agent orchestrations that dynamically execute tasks, manage state, and integrate seamlessly with production business software.

The ideal candidate is an expert Python developer with an architectural mindset, possessing a deep and proven understanding of advanced orchestration frameworks—specifically LangChain and LangGraph—to deliver autonomous, production-grade AI solutions.

Key Responsibilities:

Architect Agentic Workflows: Design and implement scalable, multi-agent AI architectures capable of autonomous decision-making, planning, and tool execution.
Build Robust Orchestration: Develop stateful, cyclical multi-agent graphs using LangGraph to effectively manage state transitions, agent hand-offs, and complex workflow loops.
Write Production-Grade Code: Standardize and deliver clean, scalable, and optimized Python applications, moving workflows from experimental notebooks into high-performance cloud environments.
Integration & Tooling: Connect LLMs (OpenAI, Anthropic, or open-source variants) with external enterprise APIs, relational databases, and proprietary business systems.
Implement RAG & Memory: Structure advanced Retrieval-Augmented Generation (RAG) pipelines and integrate vector databases to handle short-term and long-term memory across agents.
Performance & Guardrails: Set up robust validation, debugging, logging, and evaluation layers to monitor system accuracy, mitigate hallucinations, and ensure secure execution.

Required Technical Skills & Qualifications:

Programming & Architecture

Expert-level Python proficiency.
Deep understanding of Application Architecture patterns, API design (REST/GraphQL), and asynchronous programming.

Orchestration Frameworks

Advanced, hands-on experience with LangGraph and LangChain.
Must understand how to model cyclical dependencies, manage shared states, and establish human-in-the-loop validation.

AI & LLM Modeling

Proven experience deploying applications utilizing commercial APIs (e.g., GPT, Claude) or open-source models.
Strong grasp of structured parsing, function calling, and prompt engineering.

Data & Vector Infrastructure

Familiarity with Vector Databases (such as Pinecone, Chroma, Milvus, or Weaviate) alongside standard SQL/NoSQL systems.

Experience Level

5+ years in standard software/backend engineering, with 1–2+ years explicitly dedicated to building and deploying Generative AI or Agentic solutions to production.

Preferred Qualifications

Familiarity with alternative multi-agent frameworks such as CrewAI, AutoGen, or LlamaIndex.
Experience deploying AI systems using Docker, Kubernetes, and major cloud providers (AWS, GCP, or Azure).
Contributions to open-source GenAI tools, frameworks, or active technical community engagement.