AI / GenAI Architect

Looking for a technical candidate with Agentic AI experience and strong hands-on experience with Python.

Job Description
highly skilled AI / GenAI Architect to lead the design, development, and end-to-end operationalization of our AI infrastructure. In this role, you will be the driving force behind our agent-based architecture, responsible not only for building cutting-edge GenAI agents but also for managing the "run"—ensuring robust infrastructure, seamless production maintenance, and continuous optimization. If you excel at bridging the gap between innovative AI research and reliable, scalable enterprise operations (LLMOps/MLOps), this role is for you.

* 10+ years of experience in Software/System Architecture or Cloud Infrastructure.
* 3+ years of specific, hands-on experience deploying Machine Learning or Generative AI models into production.
* Proven track record of managing the operational "run" of live software/AI systems.

Job Responsibilities
* Architecture & Agent Development
* System Design: Design, develop, and scale an enterprise-grade AI and agent-based architecture.
* Agent Creation: Build, test, and deploy new autonomous and semi-autonomous AI agents tailored to specific business use cases (e.g., using LangChain, LlamaIndex, AutoGen, CrewAI).
* Integration: Seamlessly integrate GenAI modules, Large Language Models (LLMs), Vector Databases, and Retrieval-Augmented Generation (RAG) pipelines into existing enterprise applications.
* Infrastructure & "Run" Management (LLMOps)
* Infrastructure Provisioning: Provision, configure, and maintain the underlying cloud and AI infrastructure required to support LLM inference, vector storage, and agent orchestration.
* Production Maintenance: Take full ownership of the "run" phase of AI implementation. Ensure production agents are highly available, scalable, and secure.
* Strategy & Governance: Develop and implement a comprehensive strategy for the lifecycle management, versioning, and continuous maintenance of AI modules and agents in a live production environment.
* CI/CD Pipeline: Build and manage automated deployment pipelines for AI models and agent updates to ensure zero-downtime deployments.
* Monitoring, Evaluation & Refinement
* Performance Tracking: Implement robust monitoring systems to track the health, latency, and throughput of production agents.
* Quality & Safety Control: Continuously monitor outputs for model drift, accuracy degradation, bias, and hallucinations
* Continuous Improvement: Establish feedback loops to refine prompts, fine-tune models, update RAG knowledge bases, and improve overall agent performance based on real-world production data.

Technical Expertise:
* AI/GenAI Ecosystem: Deep expertise in LLMs (OpenAI, Anthropic, open-source models like LLaMA), prompting frameworks, and agentic orchestration frameworks (LangChain, AutoGen, Semantic Kernel).
* Programming: Strong proficiency in Python and relevant backend frameworks (FastAPI, Flask, etc.).
* Data & Storage: Experience with Vector Databases (e.g., Pinecone, Weaviate, Milvus, Qdrant) and data pipelines for RAG setups.
* Infrastructure & Cloud: Hands-on experience provisioning and managing infrastructure on AWS, GCP, or Azure (Terraform, Kubernetes, Docker).
* LLMOps / MLOps: Proven experience with AI/ML monitoring and evaluation tools (e.g., LangSmith, Weights & Biases, TruLens, MLflow).
* Architecture Pattern-Event Broker Orecherstor /SupervisorPattern
* Dashboard- Grafana