AI Engineering Lead

About the role

Blend is looking for an AI Engineering Lead to drive end‑to‑end delivery of advanced generative‑AI solutions. You will work closely with clients and internal teams to translate bold visions into production‑ready systems while mentoring junior engineers.

Key responsibilities

• Lead project delivery with clear governance, stakeholder communication and risk transparency.
• Design and build Retrieval‑Augmented Generation (RAG) pipelines, agentic frameworks and LLM‑powered products ready for production.
• Apply advanced prompt‑engineering techniques, conduct feasibility studies and select optimal approaches (prompting, RAG, fine‑tuning, classical ML).
• Develop evaluation frameworks, custom metrics and run structured experiments to validate model performance.
• Identify and categorize model failure modes such as hallucinations and retrieval misses.
• Build scalable inference infrastructure, CI/CD pipelines and automate the full MLOps/LLMOps lifecycle.
• Design APIs, micro‑services and orchestration layers optimized for latency, cost and reliability.

Required profile

• Expert‑level Python development with strong Git practices.
• Solid cloud experience (AWS, Azure preferred, or GCP) and container orchestration.
• Hands‑on RAG experience covering chunking, embeddings, retrieval and evaluation.
• Proven track record in MLOps/LLMOps using tools such as MLflow or Weights & Biases.
• Strong communication skills for engaging both engineering teams and senior stakeholders.

Required skills

• Python
• Git
• AWS
• Azure
• GCP
• Docker
• Kubernetes
• RAG
• Embeddings
• Retrieval
• Reranking
• MLflow
• Weights & Biases
• Databricks
• LLM fine‑tuning
• Agentic systems
• Infrastructure as Code
• Security
• Observability
• Classical machine learning