← Back to jobs
Phoenix, AZ, USA
No related jobs found
Core Focus: Real-time AI Architecture, GenAI, & High-Concurrency Inference.
Key Requirements:
GenAI & RAG: LLMs, Multi-Agent (MCP/A2A), Hybrid Search (Dense + BM25), Cross-encoders.
Inference Opt: Sub-100ms latency, vLLM, TensorRT-LLM, Triton, Quantization (FP8/INT4), PagedAttention.
MLOps & Infra: Kubernetes (EKS/GKE), Docker, Feature Stores (Feast/Hopsworks), Drift Monitoring (Evidently).
Data Streaming: Kafka, Flink, Spark Streaming, Redis.
Vector DBs: Pinecone, Qdrant, Milvus, Weaviate (HNSW/IVF).
Code: Python (AsyncIO, PySpark), PyTorch (LoRA/QLoRA), Airflow, MLflow.
Deployment: Canary, Blue-Green, Shadow deployments, HPA.
Must-Haves: 5+ years production ML experience, AWS/GCP/Azure
Must Have Skills / Highlights
LLMs
RAG
vLLM
TensorRT-LLM
Kubernetes
Kafka
Python
PyTorch
Vector Databases
AWS/GCP/Azure
Any Graduate
No related jobs found
← Back to jobs