SERGAS Group
Head of Agentic Engineering and Transformation
to Present
Dubai, UAE · Full-time
Promoted from AI Engineer and Digital Transformation Manager. Owns agentic engineering and transformation, with human-in-the-loop governance, code review and engineering standards. Sole architect, now building the function and its team. The systems listed at the end of this CV, apart from the personal project, were built in this role.
Head of Agentic Engineering and Transformation for a 35-year-old industrial enterprise, sole architect of its end-to-end AI and data transformation. Builds the company's data foundation from data lakes through medallion-architecture data marts and temporal knowledge graphs, then designs the multi-agent systems, fine-tuning pipelines and on-premise inference running on top of it. All AI runs on-premise for data governance. Sets the human-in-the-loop governance, code review and engineering standards, and is building the function and its team.
- Design and build multi-agent orchestrations: role-based agents, durable state, tool use, and verification loops.
- Prompt and context engineering with guardrails: chain-of-thought, ReAct, tool and function calling, and prompt-injection defence.
- Expose safe, narrow tool boundaries between models and live systems with MCP.
- Engineer agent memory and reliability: state persistence, multi-layer and reinforcement-learning memory, event-driven design, self-healing agents, and circuit breakers.
- Build retrieval-augmented generation systems: chunking, embeddings, hybrid retrieval, and reranking.
- Graph systems engineering: knowledge-graph modelling and graph-native retrieval over relationship-heavy domains.
- Embeddings and vector search: sentence-transformers, pgvector, LanceDB, Chroma, and cross-encoder reranking.
- NLP for legal and SOP reasoning as a domain skill of its own, modelling supersession, exceptions, and operationalisation so answers respect legal structure and currency.
- Run long-running training and inference loops on Apple MLX for on-device and on-premise workloads.
- Train and run inference on NVIDIA CUDA GPUs where the workload demands it.
- Parameter-efficient fine-tuning with LoRA and QLoRA on curated, PII-stripped domain data.
- On-premise model serving and quantization: oMLX, vLLM, llama.cpp, and GGUF.
- Edge and in-browser inference with WebGPU, ONNX Runtime, and WebLLM for private, low-latency inference close to the data.
- Computer vision and machine learning, extending into video and audio understanding (most recent work).
- Speech and multimodal pipelines: text-to-speech and speech-to-text.
- Build production applications across different tech stacks, chosen per environment and its constraints, rather than defaulting to one.
- Designs multi-agent workflows with durable state, MCP tool boundaries, guardrails, and verification loops.
- Builds hybrid retrieval and knowledge graphs that turn operational records into agent-accessible knowledge.
- Fine-tunes models with LoRA and QLoRA on curated, PII-stripped data; serves and quantizes models on-premise with MLX, vLLM, and GGUF.
- Develops computer vision, speech, and multimodal pipelines, with local and in-browser inference where privacy and latency matter.
- Chooses application stacks and infrastructure to match operating constraints, then delivers and maintains the systems.