LLM Development | Platforms
Capabilities:
Retrieval-Augmented Generation (RAG),
Agent/Agentic Workflows,
AI/ML Ops
Inference:
vLLM,
NVIDIA Triton Inference Server
Platforms:
Amazon Bedrock,
SageMaker Studio,
MLflow,
Databricks,
RedisVL,
Amazon Nova
OpenSearch Expertise:
Neural Search,
BM25,
Semantic Search,
Hybrid Search
Search Pipelines,
RAG Processor,
ML Inference,
Ingest Pipelines