Description

Design and maintain backend services for AI/ML workflows, owning production reliability, LLM integrations, and engineering standards.

This role is hybrid.

Responsibilities

• Design and enhance backend services in Java and Python to support AI/ML applications.
• Build and optimize LLM/GenAI integrations, managing prompt orchestration and cost/performance trade-offs.
• Own production support, including incident response, root cause analysis, and post-incident improvements.
• Implement robust testing strategies and drive code quality through reviews and established standards.
• Mentor junior developers and document architecture, troubleshooting guides, and production runbooks.

Required Skills

• 5+ years of experience building production-grade APIs and microservices (FastAPI, Flask).
• Strong proficiency in Python and Java.
• Hands-on experience with AI/LLM applications, including prompt design and orchestration frameworks.
• Experience debugging distributed systems and asynchronous workloads.
• Proficiency with cloud platforms (Azure preferred) and containerized deployments (Docker, Kubernetes).
• Strong knowledge of SQL and NoSQL data handling and API integration patterns.
• Familiarity with observability tools including structured logging, tracing, and monitoring dashboards.

Preferred Skills

• Experience in underwriting, insurance, document extraction, or NLP pipelines.
• Exposure to vector search, RAG, semantic retrieval, and model evaluation.
• Knowledge of secure coding, data privacy controls, and compliance-driven systems.

Key Skills

Education

Bachelor's degree