Senior Backend Engineer - AI Product
R
Re:Build ManufacturingHardware Product Development
Boston, Seattle, Los Angeles, or other cities with Re:Build officesFull-TimeSenior
Salary165000 - 215000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- DockerPostgreSQLPythonGCPFastAPIRedisTerraformLangChain
Requirements
- 5+ years building production backend systems
- 3+ years experience in Python
- Demonstrated proficiency using AI coding tools (Cursor, Copilot, Claude, etc.)
- Strong experience with FastAPI or similar async Python web frameworks
- Production experience with PostgreSQL, including schema design, migrations, and query optimization
- Hands-on experience with task queues and background processing (Celery, Redis, or similar)
- Understanding of API design, authentication patterns (OIDC/JWT), and service architecture
- Experience with containerized deployments (Docker) and CI/CD pipelines
- Ability to balance rapid iteration with maintainable, well-tested code
- Production experience integrating LLM APIs (Anthropic, OpenAI, etc.) and building AI-powered features with agent orchestration frameworks (LangChain, LangGraph, or similar)
- Hands-on experience with GCP services (Cloud Run, Cloud SQL, Pub/Sub, Secret Manager) and Infrastructure-as-code experience with Terraform
- Experience with data ingestion pipelines and ETL workflows
- Background in B2B SaaS platforms, project management tools, or workflow automation products
- Understanding of hardware development, engineering workflows, or project management concepts
Responsibilities
- Designing and implementing RESTful APIs with OpenAPI specs and auto-generated client SDKs using SQLAlchemy and Postgres
- Developing ingestion pipelines using Celery and Redis that connect to tools teams already use (file storage, messaging, email) and extract structured engineering artifacts from unstructured inputs
- Building and extending agentic AI workflows using LangChain, LangGraph, and related frameworks for structured data extraction, risk detection, dependency analysis, and proactive team coordination
- Integrating LLM APIs (Anthropic Claude, OpenRouter) with streaming (SSE), error handling, and cost optimization
- Deploying and operating services on GCP (Cloud Run, Cloud SQL, Memorystore) with Terraform
- Writing well-tested, maintainable code and participating in code reviews to establish engineering best practices
View Full Description & ApplyYou'll be redirected to the employer's site
