Senior AI Application Engineer

Responsibilities:
- Design, build, and operate backend services, APIs, and application components for AI Accelerator products.
- Develop Python/FastAPI or TypeScript/Node services integrating LLM APIs, retrieval systems, workflow engines, and enterprise systems.
- Execute AI Accelerator cycles (six 2-week sprints over 12 weeks) to build, test, validate, and prepare MVP increments for scaling.
- Build MCP/FastMCP services/APIs for governed agents to read/write/search and maintain structured (markdown/YAML) knowledge assets with version control, audit trails, access controls, and AWS-native integrations.
- Implement secure authn/authz patterns (BMS SSO/Cloud Creds), secrets management, input validation, and safe service boundaries.
- Build agentic workflows with LangGraph (orchestration, tools, fan-out/fan-in, durable checkpoints) and retrieval/context services using AWS data stores.
- Create CI/CD, IaC, automated tests, observability/evaluation (e.g., LangSmith), and quality/security/guardrail gates.

Qualifications & skills:
- BS+ in CS/Engineering/Science (or related); 5+ years software/cloud/platform/backend experience.
- Hands-on AWS (S3, RDS/PostgreSQL, Athena, Redis, OpenSearch, Fargate, Lambda, IAM, VPC).
- Proficiency in Python/FastAPI, TypeScript/Node; containers; CI/CD; Terraform/AWS CDK/CloudFormation.
- Experience with LLM/RAG/agentic AI (e.g., LangGraph/LangChain); MCP/FastMCP; semantic layers/SQL; evaluation-driven development.
- Experience integrating frontier LLMs via enterprise services (OpenAI/Anthropic/Gemini/Bedrock) and using AI coding tools.

Benefits (explicitly stated):
- Health coverage (medical/pharmacy/dental/vision); wellbeing programs; 401(k), disability, life/accident insurance, etc.
- Paid time off (flexible time off or vacation, plus paid holidays depending on location).

Application instructions:
- If interested but not perfectly matched, apply anyway.