Job Description:
Design RAG/LLM pipelines for experiment management, model management, feature management, and model retraining.
Design APIs for model inferencing at scale.
Proven expertise with MLflow, Sage Maker, Vertex AI, and Azure AI.
LLM Serving & GPU Architecture: Deep knowledge of GPU architectures, distributed training, and serving of large language models.
Model Fine-Tuning & Optimization: Improve latencies, accuracies, and reduce resource requirements for fine-tuning LLM/LVM models.
Dev Ops & LLMOps Proficiency: Expertise in Kubernetes, Docker, container orchestration, and LLM orchestration frameworks (Flowise, Langflow, Langgraph).
Mandatory Skill Sets
Gen AI, LLM, Hugging Face
Python, PyTorch/Tensor Flow/Keras
Langchain, Langgraph
Docker, Kubernetes
Additional Skills
Databases/Datawarehouse: DynamoDB, Cosmos, MongoDB, RDS, MySQL, PostgreSQL, Aurora, Spanner, Big Query
Cloud Knowledge: AWS, Azure, GCP
Dev Ops Tools: FluentD, Kibana, Grafana, Prometheus
Proficient in Python, SQL, Java Script

📌 Ai Architect Bengaluru
🏢 Acme Services Private
📍 Bengaluru