Backend Developer (Python – LLM APIs)

We are looking for a Backend Developer with strong Python experience to build high-performance APIs that integrate with Large Language Models (LLMs) on platforms such as Google Cloud Platform (GCP) and Microsoft Azure. The role focuses on building low-latency AI APIs, implementing prompt orchestration workflows, and optimizing requests for token usage, streaming responses, and inference latency. The ideal candidate should have experience building scalable APIs, working with cloud services, and understanding the performance considerations involved in LLM-based applications.

Responsibilities

API Development Design and develop high-performance REST APIs using Python. Build APIs that integrate with LLM services on GCP and Azure. Implement streaming responses for real-time AI applications. Optimize APIs for low latency and high throughput. LLM Integration Build prompt orchestration workflows across multiple LLM providers. Optimize requests by managing token usage and context windows. Implement streaming and asynchronous API responses for LLM outputs. Security & Identity Implement authentication and authorization using OAuth 2.0 and OpenID Connect (OIDC). Ensure APIs follow secure access patterns and proper authorization controls. Cloud & Infrastructure Deploy and manage applications using Docker containers. Work with cloud services on GCP and Azure. Collaborate with infrastructure teams on deployment and scaling. Data & Storage Work with NoSQL databases to store prompts, metadata, and responses. Design data structures optimized for AI workloads and API performance.

Qualifications

Programming Strong experience in Python Experience building REST APIs using frameworks such as FastAPI or Flask AI & LLM Integration Understanding of: Tokenization Latency considerations in LLM APIs Streaming responses Prompt orchestration concepts Security Experience implementing OAuth 2.0 Understanding of OpenID Connect (OIDC) Containers Experience building and deploying applications using Docker Databases Familiarity with NoSQL databases such as: MongoDB Firestore DynamoDB Cosmos DB

Nice to Have Experience working with GCP or Azure AI services Familiarity with LLM frameworks (LangChain, LlamaIndex, CrewAI) Experience with vector databases Understanding of RAG architectures Knowledge of observability tools (OpenTelemetry, Prometheus, Grafana)

Experience Needed : 2 - 5 years