AI Tech Architect

Role Summary

end-to-end architecture of production AI systems with a strong hands-on bias. Youll design robust, cost-efficient, and secure agentic/GenAI solutions on AWS. Part of your job will be to unblock lead developers by debugging code, optimizing performance, and guiding best practices. Expect to turn complex requirements into scalable, observable, and well-governed platforms.

Responsibilities

• Build and maintain REST/gRPC APIs with FastAPI (or Flask + Pydantic), using asyncio for I/O-heavy paths. • Implement background jobs & schedulers (Celery/RQ/Arq) and event pipelines with Amazon SQS/SNS. • Model data with SQLAlchemy (2.x) + Alembic; performance tuning for Amazon RDS (SQL Server); caching with ElastiCache (Redis). • Wrap AI components (LLM endpoints, tool/function calling, RAG services) behind stable interfaces; handle streaming, retries, and timeouts. • Integrate with enterprise applications (SAP/Salesforce/ServiceNow/Workday) using OAuth2/OIDC, robust error handling, and idempotency keys. • Enforce security & compliance using Okta for IAM, AWS Secrets Manager for credential storage, and structured input validation (JSON Schema). • Build APIs and services that integrate with AWS Bedrock models, custom RAG services, and OpenSearch Serverless vector stores. • Ensure backend observability through OpenTelemetry and Datadog, including metrics, tracing, and logging.

  • Own operability aspectsfeature flags, blue-green/canary release support, incident response workflows, and crisp documentation.

Must-Have Experience

• Define target architectures for agentic systems (planning/reasoning/tool-calling), GenAI/RAG pipelines, and evaluation loops; produce clear design documents with Flow/UML/sequence diagrams and AWS deployment topologies.
  • Size and optimize infrastructure for cost and performance: model throughput/latency, concurrency, autoscaling policies, CPU/GPU needs, memory footprints, vector index sizing, storage/egress, and token budgets. • Lead deep-dive debugging and incident resolution: profile bottlenecks, fix defects, stabilize services; pair-program with developers to raise the engineering bar. • Establish reference implementations for multi-agent frameworks (Semantic Kernel preferred; LangGraph/AutoGen/CrewAI acceptable), tool/function schemas, validation, memory, grounding, and multi-step planning. • Architect retrieval and hybrid search systems: ingestion, chunking, embeddings, ranking, caching, freshness, and grounding; evaluate recall, precision, and hallucination risk. • Productionize on AWS using Amazon EKS, S3, SQS/SNS, and AWS Bedrock; integrate identity (Okta/IAM), secrets (AWS Secrets Manager), eventing, and observability; enforce SLIs/SLOs and error budgets .
• • 710 years in software/AI engineering with at least 4+ years building GenAI applications and 2+ years architecting production agentic systems.
  • Strong hands-on expertise in Python 3.11+ (typing, asyncio, packaging, profiling, pytest); able to dive into code, fix bugs, and optimize performance-critical paths. • Experience with one or more agent frameworks (Semantic Kernel, LangGraph, AutoGen, CrewAI) and function/tool calling with schema and argument validation. • Proven design of GenAI/RAG/hybrid retrieval systems using AWS Bedrock, OpenSearch Serverless, or other vector databases; grounding and retrieval evaluation experience. • Deep knowledge of AWS architecture: Amazon EKS, Bedrock, S3, SQS/SNS, RDS (SQL Server/PostgreSQL), ElastiCache (Redis), Secrets Manager, IAM/Okta, Kong API Gateway, OpenSearch Serverless, and Datadog.

Nice to Have

• Multi-agent orchestration patterns: task decomposition, coordinator-worker, human-in-the-loop, graph-based planning.
  • Deep expertise with vector databases and retrieval: OpenSearch Serverless, Pinecone, pgvector, Redis. • Evaluation frameworks: red teaming, automated guardrails, regression testing, rollout gates, canary deployments. • Frontend integration for agent UIs (streaming responses, tool traces), secure connector APIs, and AuthN/Z best practices. • Policy-as-code (OPA) and multi-tenant architecture (RBAC, quotas, usage metering). • Knowledge of Kong API Gateway, LaunchDarkly/Flipt for feature management, and NeMo Guardrails for runtime safety.

Tech Stack (our core; equivalents welcome)

• Python 3.11+, FastAPI, Pydantic v2, SQLAlchemy 2.x, Alembic, pytest.
  • Amazon EKS, AWS Bedrock, Amazon SQS/SNS, Amazon RDS (SQL Server/PostgreSQL), ElastiCache (Redis). • Amazon S3 for storage, Amazon ECR for container images, OpenSearch Serverless for vector storage. • AWS Secrets Manager, Okta IAM, NeMo Guardrails, Kong API Gateway. • OpenTelemetry + Datadog for observability and monitoring. • Custom RAG Services, Bedrock Knowledge Base, and LLM evaluation with Phoenix, Arize, and Promptfoo.