Senior AI Engineer - Enterprise RAG, LangGraph & AI Agent Development
Budget / SalaryHourly project
TypeFreelance project
LocationRemote
Posted1 hour ago
We're looking for an experienced AI/Full-Stack Engineer to help us build and deploy production-ready AI applications for enterprise workflows.
The ideal candidate has strong hands-on experience with Python, FastAPI, LangGraph, RAG pipelines, and LLM integrations. We need someone who can go beyond basic AI prototypes and deliver scalable, secure, and reliable solutions.
Key Responsibilities:
- Design and develop enterprise RAG systems with document ingestion, embeddings, vector search, and reranking.
- Build autonomous AI agents using LangGraph, LangChain, and tool-calling workflows.
- Integrate OpenAI, Anthropic, AWS Bedrock, and third-party APIs.
- Develop scalable backend services using Python, FastAPI, Django, or Flask.
- Implement vector databases such as Pinecone, Qdrant, pgvector, or Weaviate.
- Deploy AI applications on AWS, GCP, or Azure using Docker, Kubernetes, and CI/CD.
- Implement authentication, security, observability, LLM evaluation, and monitoring.
Nice to Have:
MCP, Neo4j, Redis, Kafka, Terraform, multi-agent architecture, and enterprise SaaS integrations.
What We're Looking For:
Someone who has already deployed real AI applications into production, understands enterprise architecture, and can independently handle technical challenges from backend development to cloud infrastructure.
To Apply:
Please share 1–2 production AI projects you've personally worked on, including the architecture, technologies used, your specific contributions, and the most challenging technical problem you solved.
We're particularly interested in engineers with real-world experience building enterprise AI agents and RAG systems, not just proof-of-concept applications.
The ideal candidate has strong hands-on experience with Python, FastAPI, LangGraph, RAG pipelines, and LLM integrations. We need someone who can go beyond basic AI prototypes and deliver scalable, secure, and reliable solutions.
Key Responsibilities:
- Design and develop enterprise RAG systems with document ingestion, embeddings, vector search, and reranking.
- Build autonomous AI agents using LangGraph, LangChain, and tool-calling workflows.
- Integrate OpenAI, Anthropic, AWS Bedrock, and third-party APIs.
- Develop scalable backend services using Python, FastAPI, Django, or Flask.
- Implement vector databases such as Pinecone, Qdrant, pgvector, or Weaviate.
- Deploy AI applications on AWS, GCP, or Azure using Docker, Kubernetes, and CI/CD.
- Implement authentication, security, observability, LLM evaluation, and monitoring.
Nice to Have:
MCP, Neo4j, Redis, Kafka, Terraform, multi-agent architecture, and enterprise SaaS integrations.
What We're Looking For:
Someone who has already deployed real AI applications into production, understands enterprise architecture, and can independently handle technical challenges from backend development to cloud infrastructure.
To Apply:
Please share 1–2 production AI projects you've personally worked on, including the architecture, technologies used, your specific contributions, and the most challenging technical problem you solved.
We're particularly interested in engineers with real-world experience building enterprise AI agents and RAG systems, not just proof-of-concept applications.
Apply on Freelancer →
Project sourced from Freelancer.com. Applications happen directly on the original platform — we never collect your data.