Senior Software Engineer

AI Evaluation Engineer (LLMOps / AI Platform)

We're partnering with a leading technology company to hire an AI Evaluation Engineer who will play a key role in building scalable evaluation frameworks for AI agents and LLM-powered products. This is an opportunity to work on cutting-edge GenAI platforms, improving AI quality, reliability, and observability across multiple production use cases.

What You'll Be Doing

• Partner with AI product teams to improve the quality and performance of AI agents.
• Design and maintain evaluation datasets, regression test suites, automated evaluation pipelines, and quality dashboards.
• Develop evaluation methods including LLM-as-a-Judge, multi-turn conversations, tool/MCP evaluation, agent trajectory analysis, and SOP adherence.
• Build reusable platform capabilities and developer tooling that support multiple AI products.
• Improve AI observability by instrumenting distributed systems and ensuring traceability for debugging and automated evaluation.
• Integrate evaluation workflows into CI/CD pipelines and model release processes.
• Conduct experiments across models, retrieval strategies, embeddings, and agent architectures to optimise quality, latency, and cost.
• Drive continuous improvements to AI evaluation tooling, documentation, and engineering best practices.

Requirements

• At least 2 years of relevant experience in AI platform engineering, LLMOps, AI evaluation, or related software engineering roles.
• Hands-on experience with most of the following technologies:
• EvalsHub, LangSmith, LangGraph/LangChain
• FastAPI, Temporal, Grafana, Redis (or similar technologies)
• React & TypeScript for developer-facing tools
• Experience building reusable AI platform capabilities across multiple products.
• Strong analytical and problem-solving skills, particularly in handling geo-spatial or large-scale data.
• Excellent stakeholder management and cross-functional communication skills.
• Detail-oriented with a data-driven mindset focused on continuous improvement.

Experience with one or more of the following:

• LLM-as-a-Judge frameworks
• Multi-turn or agent evaluation
• Tool/MCP evaluation
• Agent trajectory analysis
• Text-to-SQL or Text-to-DSL
• RAG, semantic search, embeddings, or model benchmarking

Why This Opportunity

• Build production-grade AI evaluation systems used across multiple AI products.
• Work with modern GenAI, LLMOps, and observability technologies.
• Influence AI quality, reliability, and platform engineering at scale.
• Collaborate closely with AI researchers, platform engineers, and product teams in a highly technical environment.

If you're passionate about AI infrastructure, LLM evaluation, and building scalable AI platforms, I'd be happy to share more details.