Search Jobs
Search by job, company or skills
Search by job, company or skills
• Design, develop, and deploy AI agents and Retrieval-Augmented Generation (RAG) systems for production-grade AI workflows.
• Build and optimize agent workflows using agentic frameworks (e.g., Mastra AI or similar).
• Implement RAG pipelines with vector databases and semantic search, integrating LLMs (OpenAI, Anthropic, etc.) within applications.
• Develop backend services using Node.js and TypeScript, ensuring system scalability, security, and observability.
• Optimize prompt engineering, embeddings, and retrieval strategies for AI model accuracy and performance.
• Collaborate with product and engineering teams to translate business requirements into AI-driven solutions.
Job ID: 145445307
Skills:
Python, LangChain, AI Agents, Vector databases, AI memory frameworks, LangFlow, Generative AI architectures, Agentic AI systems, LangGraph, semantic search, Embedding models, Tool calling frameworks, MCP Server implementation, Function calling, RAG pipelines, Memory sharing architectures, Multi-agent orchestration
Skills:
Oauth, Unit Testing, Pytest, Node.js, Sql, Docker, Jest, Python, LangChain, smolagents, DeepEval, NoSQL databases, Fast API, Jaeger, Retrieval-Augmented Generation, LangGraph, Tempo, RESTful API design, Ragas, Google ADK, TruLens, uv package manager
Skills:
Tensorflow, Pytorch, Python, LLM Fine-Tuning, Edge On-device AI Deployment, TensorRT, RAG Pipelines, Pinecone, llama.cpp, Optimization, ONNX, Vector Databases, GGUF, semantic search, FAISS, Model Quantization, Transformer Architectures, ChromaDB, Generative AI LLMs, Embedding Models, Prompt Engineering
Skills:
Api, Python, LangGraph, Agentic AI, Langchain, LLMs
Skills:
Devops, FastAPI, Rest Apis, Python, LangChain, Qdrant, Pinecone, LLM systems, Agentic Workflows, LangGraph, Chroma, RAG, Weaviate, Vespa, LLM evaluation
We don’t charge any money for job offers
