AI Engineer

About the role

Datum Labs is looking for an AI Engineer to design and ship intelligent, large‑language‑model (LLM) powered products. The role sits at the crossroads of applied AI research and production engineering, turning cutting‑edge generative AI advances into reliable features that users depend on.

Key responsibilities

• Design and build end‑to‑end LLM applications, including retrieval‑augmented generation (RAG) pipelines, AI agents, and copilot‑style features.
• Evaluate and select appropriate foundation models (e.g., OpenAI, Anthropic, open‑source) for specific use cases.
• Develop prompt‑engineering strategies and manage prompt versioning across environments.
• Construct retrieval systems using vector databases such as Pinecone, Weaviate, or pgvector to ground LLMs in company‑specific knowledge.
• Instrument and monitor AI systems for accuracy, latency, cost, and safety in production.
• Stay up‑to‑date with emerging GenAI tooling and integrate relevant advances into the tech stack.
• Collaborate with product, design, and engineering teams to translate AI capabilities into tangible product value.

Required profile

• At least 2 years of experience in a technical role (software engineering, data science, ML research, etc.) with a track record of shipping production‑grade products.
• Hands‑on experience building and deploying LLM‑based applications.
• Strong problem‑solving mindset and ability to choose between simple prompts and complex agents.

Required skills

• Python programming.
• LLM frameworks such as LangChain or LlamaIndex.
• Experience with vector databases (Pinecone, Weaviate, pgvector) and vector search.
• Solid understanding of RAG architectures, embedding models, and retrieval techniques.
• Prompt engineering and LLM evaluation methodologies.
• Working with cloud‑hosted model APIs (OpenAI, Anthropic) and open‑source models.