Java, Sql, MLops, Python, LangChain, LLaMA, Data preprocessing, LLMOps, Claude, Pinecone, vLLM, Feature engineering, LMDeploy, LangGraph, FAISS, Milvus, OpenAI, Gemini, Weaviate, Model evaluation

Spark SQL, Tensorflow, Pytorch, Linux, Apache Kafka, Databricks, Api, Keras, Python, Gemini API, Ai, OpenAI API, Apache Parquet, AI Evaluation, low latency, Responsible AI, Claude API, Gemini, Model Quantisation, Prompt Injection

Celery, Neo4j, Elasticsearch, Python, FastAPI, Kubernetes, Airflow, pgvector, Argo Workflows, Qdrant, Pinecone, Prefect, OpenSearch, LangGraph, Temporal, DSPy, Microsoft AutoGen, Haystack, LangChain, CrewAI, PydanticAI, Semantic Kernel, Dagster, Milvus, Weaviate, LlamaIndex

Phoenix, Datadog, Python, LLM-based systems, OpenTelemetry, Langfuse, evaluation frameworks, multi-agent environment, Arize

Tensorflow, Cloud Services, Pytorch, Python, machine learning frameworks, AI-based video processing, DevOps practices, Azure AI, video analytics

API design, Data Architecture, Microservices, LLM integration patterns, Prompt engineering, Model-agnostic abstraction layers, Containerisation, RAG architectures

Databases, Apis, Distributed Systems, System Design, AI reliability evaluations, production risks, message queues, LLM products, product analytics, Infrastructure, Caching, frontend systems, agentic AI systems, prompting, RAG, guardrails

Machine Learning, Distributed Systems, Saas, tool integration, retrieval-based architectures, orchestration technologies, modern LLMs, prompt optimisation, Ai, AI agents, architectural standards