Description

You will design and deploy production-grade LLM backend services and agentic workflows on AWS.

This role is on-site.

Responsibilities

• Build and maintain LLM-powered backend services using Python and FastAPI for chat, search, and summarization.
• Design and implement end-to-end RAG pipelines, covering ingestion, chunking, embeddings, retrieval, and reranking.
• Develop agentic workflows supporting multi-step automation, tool calling, orchestration, and state management.
• Deploy GenAI workloads on AWS using ECS, Lambda, S3, SQS, DynamoDB, and OpenSearch.
• Implement security controls, including auth, authorization, secrets handling, and prompt-injection defenses.

Required Skills

• 10+ years overall IT experience in backend/API engineering and cloud deployments.
• 2+ years hands-on GenAI/LLM experience delivering production features.
• 6+ years strong proficiency in Python, including clean coding and performance tuning.
• 5+ years building REST APIs/microservices with strong API design and error handling.
• 5+ years experience with FastAPI, including middleware and dependency injection.
• Proven experience building RAG systems end-to-end, tuning retrieval and grounding.
• Experience with agentic patterns such as tool calling and memory/state management.
• 5+ years AWS experience using ECS, Lambda, S3, SQS, DynamoDB.
• Strong system design capability regarding scalability, caching, and resilience.

Key Skills

Education

Any Gradute