12 of 12 Permanent Faiss Jobs

Azure OpenAI, and open-source alternatives (Llama, Mistral). Experience with prompt engineering, fine-tuning, RAG (Retrieval Augmented Generation) architectures, vector databases (Pinecone, ChromaDB, FAISS), embeddings, and building AI-powered automation solutions that leverage natural language understanding. Appian BPA Platform - Strong experience with Appian low-code platform including process modelling ...

Azure OpenAI, and open-source alternatives (Llama, Mistral). Experience with prompt engineering, fine-tuning, RAG (Retrieval Augmented Generation) architectures, vector databases (Pinecone, ChromaDB, FAISS), embeddings, and building AI-powered automation solutions that leverage natural language understanding. Appian BPA Platform - Strong experience with Appian low-code platform including process modelling ...

Hands on experience with LLM APIs or open source models such as Llama or Mistral Experience building RAG systems with vector databases such as FAISS, Pinecone or Weaviate Ability to evaluate and improve prompts and retrieval quality using clear metrics Understanding of safety practices such as PII redaction and content ...

consumer behavioural or market data is desirable. Comfortable working within agile engineering teams and enterprise environments. Desirable Skills Experience with vector databases such as FAISS, Pinecone, or Weaviate. Knowledge of enterprise scale Retrieval Augmented Generation systems. Experience within global manufacturing, engineering, or industrial environments. Understanding of data governance, security ...

Python development experience Hands-on experience with Generative AI frameworks (LangChain, LlamaIndex, Haystack) and LLM APIs Knowledge of prompt engineering, vector databases (Pinecone, ChromaDB, FAISS), and model fine-tuning Cloud deployment experience with Docker/Kubernetes Understanding of transformer architectures, AI/ML principles, and MLOps Experience developing REST APIs ...

Python development experience Hands-on experience with Generative AI frameworks (LangChain, LlamaIndex, Haystack) and LLM APIs Knowledge of prompt engineering, vector databases (Pinecone, ChromaDB, FAISS), and model fine-tuning Cloud deployment experience with Docker/Kubernetes Understanding of transformer architectures, AI/ML principles, and MLOps Experience developing REST APIs ...

6+ years of Python development with hands-on experience in Generative AI Strong experience with LLM APIs, prompt engineering, and vector databases (Pinecone, ChromaDB, FAISS) Proven team leadership and mentoring skills ; managing 3-5 engineers Cloud deployment experience with Docker/Kubernetes Deep understanding of transformer architectures, AI/ ...

6+ years of Python development with hands-on experience in Generative AI Strong experience with LLM APIs, prompt engineering, and vector databases (Pinecone, ChromaDB, FAISS) Proven team leadership and mentoring skills ; managing 3-5 engineers Cloud deployment experience with Docker/Kubernetes Deep understanding of transformer architectures, AI/ ...

with AWS Bedrock and Generative AI solutions. Proficiency in Python (preferred) and/or NodeJS. Experience with LLMs, prompt engineering, RAG, vector databases (Pinecone, FAISS, OpenSearch, etc.). Strong experience with Terraform and Infrastructure-as-Code. CI/CD experience using GitLab, GitHub, or Jenkins. Experience with Docker and Kubernetes ...

Expertise in FastAPI for backend development Experience with LangChain and LangGraph Hands-on experience with Retrieval-Augmented Generation (RAG) Proficiency in vector databases (Milvus, FAISS, or similar) Database integration (MongoDB/PostgreSQL, GraphDB) Experience integrating AWS Bedrock models Desired Qualifications: Prompt engineering for optimizing LLM interactions Ability to design ...

work. Agentic/orchestration: LangChain , LlamaIndex , LangGraph , AutoGen/CrewAI MLOps/workflows: MLflow , Kubeflow, Airflow/Prefect, DVC, Feast Vectors/NLP: pgvector , FAISS/Milvus/Qdrant , Transformers/embedding libraries Automation/low-code OSS: Robot Framework, TagUI , n8n, Appsmith Observability: OpenTelemetry Company Overview: Keurig Dr Pepper ...

NoSQL databases, ensuring seamless integration with AI-driven microservices and retrieval-augmented generation (RAG) models. Collaborate with AI engineers to incorporate vector databases (Pinecone, FAISS, ChromaDB) and AI retrieval pipelines into enterprise software. Develop, optimize, and deploy LLM prompt engineering solutions, embedding models, and AI-enhanced workflows targeting healthcare domain … OpenAI GPT, Hugging Face Transformers, LangChain, LlamaIndex. Familiarity with retrieval-augmented generation (RAG) concepts, LLM prompt engineering, embeddings, and vector similarity search using Pinecone, FAISS, or ChromaDB. Solid understanding of Unix/Linux environments, big data pipelines, and continuous integration/continuous deployment (CI/CD) practices in Agile settings. ...