AI Architect in Torrance, CA (3 days Hybrid

AI Architect

Torrance, CA (3 days Hybrid)

Contract

AI Architect with AWS bedrock, langchain, RAG, GraphQL, PostgreSQL, TensorFlow, PyTorch

Job Details:

• Design multi-layered AI solutions balancing compute efficiency contextual fidelity and algorithmic adaptability retrieval reasoning planning tooluse
• Develop advanced RAG pipelines leveraging vector databases eg ChromaDB Milvus FAISS and embedding strategies for contextual accuracy
• Integrate AI capabilities with enterprise systems via REST and GraphQL APIs ensuring secure and scalable interoperability
• Establish best practices for algorithm selection and layering combining neural models symbolic reasoning and toolbased agents for optimal performance
• Collaborate with crossfunctional teams to embed AI agents into business workflows and align with compliance and governance standards
• Implement structured output validation and schema enforcement using Pydantic FastAPI and JSON Schema for robust data integrity
• Optimize compute resources and latency tradeoffs across cloud hybrid and edge environments for highperformance AI workloads
• Define observability baselines telemetry tracing evaluation metrics and rollout strategies for safe iterative deployments

Required Skills

• Programming Architecture Python 310 Async design modulardistributed architecture microservices
• LangChain Ecosystem LangChain LangGraph prompt templates agent orchestration patterns
• AIML Frameworks OpenAI API HuggingFace Transformers TensorFlow PyTorch experience with finetuning and inference optimization
• Data Context Management SQLAlchemy PostgreSQL JSON Schema Mapping feature engineering and contextual pipelines
• Vector Databases Semantic Search ChromaDB Milvus FAISS embedding optimization and similarity search strategies
• Algorithmic Design Strong understanding of algorithm layering retrieval reasoning planning hybrid AI approaches and computeaware model selection
• API Integration Security REST GraphQL OAuth enterprisegrade security practices
• DevOps CICD Git Docker Azure DevOps or equivalent FastAPI Uvicorn containerized deployments and automated pipelines
• Agentic Capabilities Reasoning adaptation tool calling MCPbased solutions ReAct agents Supervisormultiagent coordination
• Performance Optimization Distributed compute strategies GPUTPU utilization quantizationpruningdistillation caching batching

Skills

Mandatory Skills : Architectural diagrams