Description

You will design and build multi-agent systems and RAG services, focusing on reliable LLM integration and evaluation.

This role is remote.

Responsibilities

• Design multi-agent systems using LangGraph or Semantic Kernel, implementing planning, tool-use, and delegation.
• Build Retrieval-Augmented Generation (RAG) services, including chunking, embeddings, indexing, and hybrid/vector search.
• Implement ingestion pipelines for diverse data sources using Airflow, Prefect, or Ray.
• Integrate model gateways (OpenAI, Azure OpenAI, Bedrock, or Vertex AI) and Model Context Protocol (MCP) servers.
• Evaluate LLM outputs and RAG applications using Promptfoo and RAGAs, maintaining regression suites and golden sets.

Required Skills

• 8+ years of experience with Python as the primary language.
• Experience with LangGraph or Semantic Kernel for agent orchestration.
• Hands-on experience with at least one major cloud platform (Azure, AWS, or GCP).
• Knowledge of Java, Node.js, or Go is optional but beneficial.
• Experience with FastAPI for service development.
• Understanding of vector databases (pgvector, Pinecone, Weaviate, OpenSearch).
• Bachelor's degree in Computer Science or related field.

Preferred Skills

• Experience packaging services as containers and deploying to Kubernetes with Helm/Argo CD.

Key Skills

Education

Bachelor's degree