Description

You will design, build, and deploy production-grade AI applications, focusing on agentic workflows, RAG architectures, and scalable backend systems.

This role is on-site.

Responsibilities

• Develop high-quality, secure, and scalable software solutions using Python and modern AI frameworks.
• Design and implement Retrieval-Augmented Generation (RAG) systems, including embeddings, chunking, and vector retrieval optimization.
• Build agentic AI workflows and multi-step reasoning systems for production environments.
• Deploy cloud-native AI applications on AWS using Bedrock, SageMaker, Lambda, and API Gateway.
• Collaborate with cross-functional teams to define requirements, conduct code reviews, and ensure system reliability and observability.

Required Skills

• 9+ years of software engineering experience with deep proficiency in Python.
• Hands-on experience with AI frameworks such as LangChain, LangGraph, and HuggingFace.
• Practical implementation of RAG architectures, including vector-enabled datastores (e.g., OpenSearch, pgvector).
• Experience deploying AI solutions on AWS, specifically SageMaker, Lambda, and API Gateway.
• Proven ability to build full-stack AI applications with strong focus on security and performance.
• Implementation of effective unit testing and secure coding practices.
• Experience with CI/CD pipelines for AI workloads.

Preferred Skills

• End-to-end MLOps/LLMOps experience, including model lifecycle management and monitoring.
• Experience leading junior engineers and driving engineering best practices.

Key Skills

Education

Bachelor's degree