About the role
Responsibilities:
- Build scalable and reusable AI services, APIs, SDKs, and backend components.
- Design and implement production-grade RAG pipelines, including embeddings, chunking, retrieval, vector search, and reranking.
- Integrate LLM APIs, structured outputs, function/tool calling, and multimodal capabilities.
- Build AI orchestration and agentic workflows using LangChain, LangGraph, or equivalent.
- Work with vector databases such as Pinecone, Weaviate, Chroma, FAISS, OpenSearch, or Elasticsearch.
- Develop production-ready AI systems with evaluation, guardrails, observability, and governance.
Requirements:
- 7-10 years of software/backend engineering experience.
- Node.js and TypeScript are mandatory.
- Strong RAG + LLM experience.
- LangChain / LangGraph or equivalent.
- Embeddings, vector search, and vector databases.
- AI agents/tool calling/orchestration.
- Strong experience building reusable APIs, SDKs, or platform components.
- Good understanding of scalable backend and AI application architecture.
Good to Have:
- AI evaluation/hallucination detection.
- Fine-tuning / LoRA / QLoRA.
- AI security, guardrails, and PII handling.
- Hugging Face / Ollama
- React / Angular / Web Components.