AI Engineer

Company Description

Blend is a premier AI services provider, committed to co-creating meaningful impact for its clients through the power of data science, AI, technology, and people. With a mission to fuel bold visions, Blend tackles significant challenges by seamlessly aligning human expertise with artificial intelligence. The company is dedicated to unlocking value and fostering innovation for its clients by harnessing world-class people and data-driven strategy. We believe that the power of people and AI can have a meaningful impact on your world, creating more fulfilling work and projects for our people and clients. For more information, visit www.blend360.com

We are seeking an Lead AI Engineer to contribute to our next level of growth and expansion.

Job Description

Leadership and Delivery

• Lead project delivery end to end, with clear governance, stakeholder communication, and accountability for outcomes
• Build and mentor a high-performing AI engineering team, establishing technical standards and fostering a culture of quality and pragmatism
• Own proposals and new business initiatives, defining technical feasibility and communicating risks and tradeoffs clearly to clients
• Define what AI systems should and should not attempt, setting realistic expectations and being upfront about limitations
• Conduct technical reviews and architectural assessments to maintain high standards across projects and team

AI Development

• Guide the design and delivery of RAG systems, agentic frameworks, and LLM-powered solutions that are robust enough for production
• Lead the application of advanced prompt engineering techniques including instruction design, few-shot sets, structured outputs, and tool/agent prompts
• Run feasibility assessments to choose the right approach for each problem: prompting, RAG, fine-tuning, or classical ML
• Mentor engineers on end-to-end AI system design and production deployment practices

Evaluation and Quality

• Design evaluation frameworks including LLM-as-a-judge approaches, metric creation (recall@k, precision@k), and go/no-go gates
• Lead structured experiments across prompts, retrievers, chunking strategies, and models, grounded in evidence not intuition
• Establish team practices for identifying and categorising model failures including hallucinations, retrieval misses, and instruction-following errors