Infrastructure Engineer

AI Infrastructure Engineer (Vector DB, LangChain)

Location: Hybrid

Start: ASAP

Duration: 12 months renewable

Build scalable, production-grade GenAI stacks with performance in mind

We’re hiring an AI Infrastructure Engineer to design and implement vector-native architectures for real-time GenAI use cases. From retrieval pipelines to LangChain orchestration, you’ll be working deep in the stack.

Key Responsibilities:

• Design infrastructure for retrieval-augmented generation (RAG) workflows
• Integrate vector databases (Pinecone, FAISS, Weaviate) into LLM pipelines
• Optimise latency, concurrency and fault-tolerance for LLM-driven systems
• Work closely with ML and backend engineers on full-stack GenAI systems

Key Skills & Competencies:

• 4+ years in backend, MLOps or infra-focused engineering roles
• Proficient in Python, FastAPI, Docker, Terraform, and vector search tools
• Experience deploying LangChain, LlamaIndex or similar
• Bonus: familiarity with Snowflake Cortex or Databricks AI functions

If you enjoy building the plumbing that makes GenAI systems usable at scale, this is your role.