Senior/Staff/Senior Staff AI Infrastructure & Applied AI Engineer

The success of any AI initiative depends on one critical factor: people.

Not just skills, but judgement, experience, and the ability to operate in real-world environments. Nexus People is a specialist consulting firm dedicated to supporting organisations build their future with top AI talent & capabilities.

This is an open call to identify candidates across a family of related engineering roles covering the design, optimisation, and deployment of large-scale AI systems. Roles are available at Senior, Staff, and Senior Staff level, spanning two broad areas of focus:

• Machine learning infrastructure and performance engineering, covering how large models are served, scaled, and made efficient in production.
• Applied AI engineering for agent-based and automation-driven systems, covering how models are integrated into tools, workflows, and decision-making pipelines.

Candidates working in either of these areas, or in adjacent disciplines within applied AI and machine learning systems engineering, are invited to express interest.

• Build and scale inference platforms and serving frameworks for large language, vision-language, and diffusion models.
• Contribute to LLM serving and orchestration packages such as vLLM, SGLang, TGI, Triton Inference Server, Dynamo, or LLM-d.
• Transform and optimise models for efficient inference using PyTorch, ONNX, and graph capture/compilation approaches such as torch.compile and TorchDynamo.
• Design and implement specialised kernels and fusion operations, for example in Triton or CUDA, for performance-critical workloads.
• Analyse and improve throughput and latency across batching, parallelism, KV-cache management, and speculative decoding strategies.
• Design agent architectures that decompose complex goals into executable steps, integrate LLMs with external tools, APIs, and vector databases, and implement memory, guardrail, and monitoring systems for autonomous agents.
• Profile, debug, and resolve complex performance or stability issues to root cause.
• Collaborate with compiler, firmware, platform, and customer-facing teams to move solutions from research through to commercial deployment.
• Engage with open-source AI/ML communities to evolve serving and optimisation frameworks.

Looking to advance your Development & Programming career with relocation support? Explore Development & Programming Jobs with Relocation Packages that include comprehensive packages to help you move and settle in your new role.

• Strong Python development skills for large-scale software projects.
• Hands-on experience with PyTorch, and, depending on specialisation, ONNX, LangChain, or comparable frameworks.
• Deep understanding of transformer-based architectures, attention mechanisms, and mixture-of-experts models.
• Strong computer science fundamentals, including algorithms, data structures, and parallel or distributed programming.
• Understanding of computer architecture, ML accelerators, and distributed systems, or, for agentic-focused candidates, cloud infrastructure (AWS, Azure, GCP).
• Experience analysing, profiling, and optimising deep learning workloads for throughput and latency.
• Experience with RESTful APIs, vector databases, and semantic search (for agentic/applied AI candidates).
• Strong communication and problem-solving skills, with the ability to operate across the full lifecycle from research and prototyping through to commercial deployment.
• MSc in Computer Science, Machine Learning, Computer Engineering, Electrical Engineering, or a related field, or equivalent practical experience.

• Open-source contributions to any GenAI, LLM serving, or agent-orchestration package.
• Experience architecting and developing large-scale distributed systems.
• High-level kernel design experience (PyTorch, CUDA, Triton).
• Experience with continuous batching, disaggregated serving, or KV-cache management at scale.

Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.

• Background in numerical methods, accuracy evaluation frameworks, or ML compilers.
• PhD in Computer Science, Computer Engineering, Machine Learning, or a related field.

• Bachelor's degree in Engineering, Information Systems, Computer Science, or a related field and 4+ years of Software Engineering or related work experience; OR
• Master's degree in Engineering, Information Systems, Computer Science, or a related field and 3+ years of Software Engineering or related work experience; OR
• PhD in Engineering, Information Systems, Computer Science, or a related field and 2+ years of Software Engineering or related work experience.
• 2+ years of work experience with a programming language such as C, C++, Java, or Python.

• Salary, stock, and performance-related bonus
• Employee stock purchase scheme
• Matching pension scheme
• Maternity/Paternity Leave
• Education Assistance
• Relocation and immigration support (if needed)
• Life, Medical, Income, and Travel Insurance
• Subsidised memberships for physical and mental well-being
• Bicycle purchase scheme