Description

You build scalable AI platforms, RAG pipelines, and agentic workflows.

This role is hybrid.

Responsibilities

• Develop scalable AI-enabled platforms and APIs using Python, TypeScript, or Node.js.
• Build and optimize RAG and semantic search pipelines with vector databases and embedding models.
• Design agentic AI workflows involving multi-step reasoning and function calling.
• Create ingestion and enrichment pipelines for structured and unstructured data.
• Partner with Product and Engineering teams to integrate LLM observability and quality metrics.

Required Skills

• 5+ years of software engineering experience with Python, TypeScript, or Node.js.
• Deep knowledge of LLM integration, including OpenAI, Anthropic, Claude, or Gemini.
• Experience with prompt engineering, context management, and grounding/citation strategies.
• Proficiency with RAG frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
• Familiarity with vector databases like Qdrant, Pinecone, Weaviate, or pgvector.
• Strong understanding of REST/GraphQL APIs and containerization with Docker/Kubernetes.
• Experience with Neo4j or knowledge graphs is a plus.

Preferred Skills

• Experience with Go and event-driven architectures.
• Background in building multi-step agentic AI systems.

Key Skills

Education

Any Gradute