Design, develop, and maintain LLM-powered services, including prompt pipelines, embeddings, vector indexing, and retrieval logic
Build and maintain Python backend services with scalable, reliable architecture
Integrate internal and external APIs to support end-to-end AI workflows
Implement and optimize RAG pipelines, chunking, reranking, and text-processing components
Collaborate with engineers and cross-functional partners to turn requirements into solutions
Write clean, tested, well-documented code and participate in high-quality code reviews
Ensure security, privacy, and compliance in all data-handling and code practices
Troubleshoot and optimize existing AI/ML pipelines for performance and maintainability

1+ years of strong Python engineering (OOP, typing, testing, clean architecture, PEP-8 discipline)
Proven experience deploying LLM-powered applications in production
Hands-on experience with LLM frameworks: LangChain, LlamaIndex, Sentence Transformers, vector stores, and rerankers
Understanding of embeddings / vector search techniques (cosine similarity, semantic scoring)
Backend API engineering: FastAPI or similar frameworks (Flask, Starlette), RESTful design, authentication flows
SQL proficiency: schema design, indexing, query optimization
SQLAlchemy experience preferred
Cloud experience: Azure preferred (App Services, Storage, Cognitive Search, Key Vault)
Production-grade code practices: error handling, logging, documentation, and maintainability
Strong Git workflow discipline (PR quality, branching strategies, code review)
Excellent problem-solving and communication skills, comfortable working independently and asynchronously across time zones
Familiarity with React/TypeScript and frontend API integration is a plus
Experience with logging/telemetry/observability tools (Application Insights, structured logging) is a plus

Contract, AI Software Engineer

Key skills