AI Architect
Irvine, CA (2-3 days / week in the client s Irvine office, 1 day in their downtown LA office, 1 day remote)
CA locals preferred
Long Term
Backend & Agent-Oriented Engineering:
- Build and maintain Python-based backend services supporting:
o Agent orchestration (supervisor/sub-agent patterns)
o APIs and system integrations
o Multi-step, asynchronous workflows
- Apply strong engineering practices (testing, code quality, error handling).
AI / LLM-Enabled Application Development:
- Deliver LLM-enabled features end to end, including:
o Prompt and context management
o Structured outputs and validation
Data Engineering for Retrieval-Based Systems:
- Design and operate retrieval pipelines to support grounding and context enrichment, including:
o Vector search and similarity retrieval
o Search and indexing solutions
o Object storage for source content and embeddings
o Caching for performance and scalability
Cloud-Native Delivery:
- Deploy and operate services primarily on AWS, following best practices for:
o IAM and security
o Scalability, resiliency, and availability
o CI/CD and environment management
Integration & UX Enablement:
- Integrate with enterprise tools and services via secure APIs and gateways.
- Support React-based front-end patterns and collaboration integrations to enable effective user experiences.
Observability & Operations:
- Implement logging, metrics, and tracing across agent workflows, model calls, and integrations.
- Support incident diagnosis, performance tuning, and ongoing optimisation.
Working with the Business
- Engage directly with business stakeholders to:
o Translate use cases into technical designs and acceptance criteria
o Communicate trade-offs across quality, cost, risk, and delivery timelines
Torque Technologies LLC is an Equal Opportunity Employer (EOE). Qualified applicants are considered for employment without regard to age, race, color, religion, sex, national origin, sexual orientation, disability, or veteran status.