Description

Define end-to-end architectures for complex Gen AI solutions, including RAG pipelines and multi-agent systems.

This role is hybrid.

Responsibilities

• Design cloud-native microservices and APIs (FastAPI, REST) to connect AI orchestrators with enterprise data backends.
• Architect multi-agent, goal-driven autonomous AI systems using LangGraph, CrewAI, AutoGen, or LlamaIndex.
• Lead evaluation, selection, and fine-tuning of proprietary APIs and open-source models based on performance and cost.
• Define cloud infrastructure scaling, GPU/TPU sizing, and orchestration layouts using Docker and Kubernetes/OpenShift.
• Embed governance and security guardrails to prevent prompt injection, data leakage, and PII exposure.

Required Skills

• 8+ years of experience in software architecture or AI engineering.
• Deep expertise in Gen AI solution design, including Retrieval-Augmented Generation (RAG) and multimodal models.
• Proficiency with Python and building microservices architectures.
• Experience with AWS and GCP cloud platforms.
• Strong knowledge of containerization and orchestration using Docker and Kubernetes.
• Hands-on experience with API frameworks such as FastAPI.
• Understanding of vector databases (Pinecone, Milvus, Weaviate, FAISS) and LLMOps/GenAIOps pipelines.
• Bachelor's degree in Computer Science or related field.

Key Skills

Education

Bachelor's degree