Responsibilities
- Design and implement complex LangGraph-based agent workflows and supervisor architectures.
- Integrate and orchestrate foundation models through Amazon Bedrock.
- Develop secure, scalable REST/OpenAPI services using Python and FastAPI.
- Build governed AI-accessible data services leveraging Databricks.
- Deploy and manage AI workloads on AWS EKS.
- Implement end-to-end tracing, evaluation frameworks, and security mechanisms for AI workflows.
AI & Agent Frameworks
- 5+ years of software engineering experience with Python.
- Hands-on production experience building Agentic AI systems.
- Expertise in LangGraph, Multi-Agent Architectures, Workflow Orchestration, and more.
Python Ecosystem
- Advanced Python development experience.
- Knowledge of FastAPI, Pydantic, Async Programming, and more.
Cloud & Containers
- Hands-on experience with AWS, Amazon EKS, Kubernetes, Docker, and Helm.
- Experience deploying and supporting AI workloads in production environments.
Data & Storage Technologies
- Experience with PostgreSQL/AWS RDS, Redis, Transactional systems, and more.
- Knowledge of caching strategies, high availability, and disaster recovery designs.
Databricks
- Experience with Databricks SQL Warehouses, Unity Catalog, Delta Lake, and more.
- Understanding of query governance and secure data access.
Observability & Monitoring
- Experience with OpenTelemetry, AI observability platforms, distributed tracing, and more.
- Knowledge of reliability engineering and performance monitoring.
Security & Compliance
- Experience working in regulated environments.
- Understanding of PHI/PII Compliance, Data Governance, API Security, and more.
Industry:
AI & Machine Learning