Job description
Qualifications
- Bachelor’s Degree
- 6+ years cloud architecture experience
- 3+ years building production GenAI/LLM systems on AWS.
- Strong Python and AWS expertise, including Lambda, ECS/EKS, S3, Sage. Maker, Docker and Kubernetes.
- Production experience with vector databases and designing ingestion + embedding pipelines for both batch and streaming workloads.
- Hands-on with prompt design, evaluation, LLM orchestration, and RAG implementation patterns.
- Experience deploying and operating model- serving or MCP – like server infrastructure (selfhosted or managed).
- Proficient with IaC and delivery tooling, including Terraform/Cloud. Formation, Git. Ops, and CI pipelines.
- Experience with model-serving infrastructure, such as Amazon Sage. Maker, NVIDIA Triton, Ray Serve, or similar platforms.
- Hands-on experience with GenAI libraries and frameworks, including Lang. Chain, Llama. Index, Hugging Face, and OpenAI APIs.
- Deep operational expertise with vector databases, such as Pinecone, Milvus, Weaviate, or Qdrant.
- AWS Solutions Architect, AWS DevOps Engineer, or equivalent industry certifications.
Responsibilities
- Cloud Architecture & Infrastructure, Design scalable, secure AWS architectures
- LLM & GenAI Platforms, Lead integration of API-based and self-hosted LLMs, implement RAG solutions
- Prompting & Evaluation, Develop prompt engineering strategies, reusable templates, and evaluation frameworks
- Vector Databases & Retrieval Pipelines, Implement and maintain vector stores (Open. Search, Pinecone, Milvus, Qdrant)
- Data Ingestion & Processing Pipelines
- Microservices & Serverless Systems
- Python Development & AI Tooling
- Security, Governance & Cross-Functional Leadership