What are the responsibilities and job description for the Agentic AI Architect position at FUSTIS LLC?
W2 Position : Principal Solution Architect – Agentic AI Platform
Location : Fort Worth, TX – Hybrid
Duration : 12 Months!!
Interview: Onsite – F2F
Job Description:
We are seeking a Principal Solution Architect with 10 years of software architecture experience to join the Agentic System Layer (ASL) team. In this role, you will define and drive the technical architecture for the airline's agentic AI platform.
Key Responsibilities
- Design and evolve the architecture for multi-agent orchestration systems, tool-use frameworks, and LLM integration pipelines.
- Establish patterns for agent reliability, observability, and guardrails at production scale.
- Lead technical design reviews and produce Architecture Decision Records (ADRs).
- Collaborate with ML Engineers and Software Engineers to ensure platform components are scalable, secure, and maintainable.
- Evaluate and integrate emerging agentic AI frameworks such as LangGraph, CrewAI, Semantic Kernel, and AutoGen.
- Define API contracts, data flow patterns, and integration standards across the AI platform ecosystem.
- Mentor engineers on best practices for building production-grade AI systems.
Mandatory Skills
- 10 years of software architecture experience, including 3 years designing AI/ML platform systems with hands-on experience in LLM orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, or similar.
- Deep expertise in:
- Distributed systems design
- Microservices architecture
- Event-driven patterns
- API design (REST/gRPC)
- Strong proficiency in Python and at least one of Java, Go, or TypeScript
- Production experience building and deploying agentic AI systems or LLM-powered applications at scale, including:
- Prompt engineering
- Tool-use patterns
- RAG pipelines
- Agent reliability and observability
Nice-to-Have Skills
- Kubernetes and container orchestration
- Cloud platforms (AWS, Azure, or GCP)
- MLOps/LLMOps tooling
- Vector databases (Pinecone, Weaviate, pgvector)
- Knowledge graphs
- Airline or travel domain experience
- TOGAF or similar architecture certification
- Multi-agent system design patterns
- Agent evaluation and benchmarking frameworks