Agentic AI Architect
Dallas, TX, NYC, Chicago, IL
Fulltime with Photon
The Agentic AI Architect will serve as the primary technical authority for designing and delivering large-scale Agentic AI solutions. This role acts as a critical bridge between product strategy, customer requirements, and engineering execution, requiring a strong blend of AI expertise, system architecture, and leadership skills.
The Architect will be responsible for leading architecture definition, driving complex proof-of-concept initiatives, enabling multi-agent system design, and managing cross-functional engineering teams. The role demands deep experience in LLM ecosystems, cloud-native platforms, and scalable system design to deliver robust, production-grade AI platforms with measurable business outcomes.
Key Responsibilities:
Solution Architecture: Lead the design and development of scalable, secure, and high-performance architectures for Agentic AI platforms using Python and modern frameworks
Technical Standards & Deliverables: Define architecture patterns, engineering standards, and best practices for development, deployment, and system scalability
Collaboration: Work closely with product managers, engineering teams, DevOps, and QA to align technical solutions with business requirements and ensure seamless system integration
Stakeholder Interaction: Lead and execute technical POCs for Agentic AI solutions, working with customer stakeholders to define success criteria, build tailored agent configurations, and demonstrate business impact
Agent Orchestration: Architect and implement multi-agent workflows using frameworks such as LangGraph, AutoGen, or CrewAI, ensuring alignment with real-world use cases
Platform Development: Design and build resilient, scalable, multi-tenant AI platforms that support continuous innovation and production deployment
Evaluation & Benchmarking: Own the design and implementation of LLM and agent evaluation frameworks, including metrics for accuracy, hallucination, safety, and performance
Performance Optimization: Optimize system architecture and infrastructure for scalability, latency, and cost-efficiency across AI workloads
Best Practices: Establish and enforce standards across MLOps, AIOps, CI/CD, model versioning, experimentation tracking, and system observability
Leadership & Mentorship: Provide technical leadership, guide architectural decisions, and mentor engineering teams to ensure high-quality delivery
Innovation & Research: Stay updated with advancements in AI, LLMs, and agentic frameworks, continuously improving system capabilities
Documentation: Create and maintain comprehensive architectural and technical documentation
Required Skills & Qualifications:
- 12+ years of experience in software engineering with strong expertise in Python and backend system development
- Extensive experience in designing scalable, secure, multi-tenant AI/ML platforms
- Deep expertise in LLMs (OpenAI, Gemini, Anthropic, Llama) and agentic AI systems
- Hands-on experience with agent frameworks such as AutoGen, CrewAI, LangGraph, and LangChain ecosystem (LangChain, LangSmith, LangFlow)
- Strong experience building RAG-based systems and working with vector databases
- Proficiency in Python ecosystem including PyTorch, Scikit-learn, LlamaIndex, and evaluation tools like DeepEval
- Deep understanding of LLM concepts (prompt engineering, fine-tuning, function/tool calling, RAG)
- Strong experience in microservices architecture, REST APIs, and event-driven systems
- Expertise in relational (PostgreSQL, MySQL) and NoSQL databases (MongoDB, Redis)
- Experience with cloud platforms (AWS, Azure, Google Cloud Platform) and cloud-native architectures
- Familiarity with Docker, Kubernetes, and modern DevOps practices
- Experience with CI/CD pipelines (Jenkins, GitLab CI, GitHub Actions)
- Strong exposure to observability tools for logging, monitoring, and tracing AI systems
- Strong understanding of system design, scalability, and engineering best practices
- Proven ability to lead architectural discussions, mentor teams, and engage with stakeholders and clients
Never miss an opportunity! Create an alert based on the job you applied for.
