Senior AI Engineer - Gravitas Recruitment Group

The Senior AI Harness Engineer joins the organisation’s AI development team to define and build the foundational engineering capabilities supporting AI models and agents at enterprise scale. This role is essential for enabling AI systems to operate securely, reliably, and efficiently across various domains within the organisation. About the Company Our client is involved in building AI capabilities across customer experience, network and service operations, enterprise solutions, and internal productivity. The organisation is focused on creating scalable, secure, and innovative AI systems. Role Overview The Senior AI Harness Engineer will lead the design and development of reusable frameworks for AI orchestration, context management, memory systems, tool integration, and evaluation. Reporting to senior technical leadership, the role involves establishing engineering standards, solving complex systemic issues, and partnering with multiple technical teams to deliver enterprise-grade AI solutions. Success hinges on delivering scalable, secure, and maintainable infrastructure to support AI deployment and continuous improvement. Key Skills & Experience • Architect and build production-grade AI harnessing frameworks and SDKs. • Design scalable evaluation and experimentation infrastructure supporting automated testing and feedback. • Develop instrumentation and observability patterns for end-to-end diagnosis of AI and agent behaviour. • Manage complex technical investigations and resolve systemic engineering issues. • Collaborate with cross-functional teams to establish production engineering standards. • Proven experience with Python, APIs, distributed systems, and automation in AI or ML environments. • Knowledge of agent architectures, context engineering, and orchestration. • Experience with enterprise security, identity management, and permission policies. • Cloud-native and distributed-system engineering expertise. • Familiarity with agent frameworks such as LangGraph or LangChain (advantageous). Nice to Have • Experience with agent or Large Language Model (LLM) frameworks. Key Responsibilities • Define architecture and set technical direction for reusable AI harness capabilities. • Build reusable SDKs, libraries, and reference implementations for AI system development. • Lead design of interfaces connecting AI agents to enterprise data and operational systems. • Develop evaluation strategies covering safety, reliability, latency, and costs. • Establish instrumentation and observability standards for AI system diagnostics. • Conduct technical investigations to resolve reliability and systemic issues. • Partner with internal teams to establish and uphold engineering standards and practices. • Evaluate emerging AI infrastructure and frameworks for potential adoption or standardisation. Requirements • Right to work in the intended location. • Educational background in Computer Science, Engineering, AI/ML, or a related discipline, or equivalent hands-on experience. • Minimum of 8 years of experience in software engineering, platform development, distributed systems, or AI/ML with production system operation. • Proficiency in Python, APIs, distributed systems, concurrency, testing, and system design. • Hands-on experience with architecting and deploying production LLM, RAG, or agentic AI systems. • Strong understanding of agent architectures, context management, and orchestration. • Experience with enterprise security protocols including identity, authn/authz, secrets management, and privilege enforcement. • Ability to influence engineering decisions as a senior technical authority. • Experience with cloud-native architectures and distributed systems. • Knowledge of agent frameworks such as LangGraph, LangChain, or similar is advantageous. This position is on-site and initially scheduled for 2 weeks, starting on 17/09/2026. If you have the relevant skills and experience, please apply with an updated CV.