Key Responsibilities
- Design and develop production-grade AI applications leveraging large language models and foundation models via AWS Bedrock and other providers
- Build scalable commercial solutions integrating advanced AI capabilities into real-world products and platforms
- Develop RAG systems, AI copilots, conversational agents, automated workflows, and AI-driven analytics
- Create pipelines for embeddings, document ingestion, knowledge indexing, and model evaluation
- Optimize latency, reliability, and cost of model inference while implementing evaluation and monitoring frameworks
- Deploy models using Docker and Kubernetes, and design high-performance AI APIs and microservices
Requirements
- 6+ years of software engineering experience with 3+ years building AI/ML-powered applications
- Hands-on experience with LLM APIs, foundation models, and production deployment
- Proficiency in Python and backend languages (Java/TypeScript/Go), AWS services (S3, Lambda, ECS/EKS), and AI orchestration frameworks
- Experience with prompt engineering, vector databases, and AI safety/guardrails
- Strong systems architecture skills with a track record of shipping real AI products