Gen AI Architect
About the role
The Gen AI Architect role is focused on designing and scaling production-grade autonomous software systems that integrate agentic AI, enterprise architecture, asynchronous backends, and real-time frontends. The position involves responsibilities such as designing multi-agent workflows, implementing memory and retrieval-augmented generation (RAG) systems, building asynchronous backends and real-time frontends, managing data and state, implementing observability and guardrails, and deploying solutions using modern DevOps practices. The ideal candidate will have significant experience in building and deploying LLM and Agentic AI applications, a strong understanding of asynchronous runtimes and system design, and relevant academic or practical qualifications.
Must have
- Minimum 8 years of overall experience
- 2–3 years of hands-on experience building and deploying production-grade LLM and Agentic AI applications.
- Strong understanding of asynchronous runtimes, system design, and agent failure modes, including infinite loops, context loss, and hallucinations.
- B.S./M.S. in Computer Science, Artificial Intelligence, or equivalent practical experience.
Technologies
- Agentic AI
- Anthropic
- AutoGen
- AWS
- Azure
- CI/CD
- CrewAI
- Cursor
- DevOps
- Docker
- FastAPI
- GCP
- Generative AI
- GitHub
- GitHub Actions
- Kubernetes
- LangGraph
- LangSmith
- LLM
- LLMOps
- MCP
- Neo4j
- Next.js
- Node.js
- Observability
- Ollama
- OpenAI
- OpenTelemetry
- pgvector
- Pinecone
- PostgreSQL
- Python
- Qdrant
- RAG
- React
- Redis
- Tailwind CSS
- TypeScript
- Vector Databases
- vLLM
- Weaviate
- WebSockets