Junior AI Engineer · London, UK
Raian Khan
IT Engineer at Odgers
Building production AI systems — fine-tuned LLMs, RAG pipelines, and cloud-native inference platforms — with the infrastructure depth to ship them.
IT Engineer at Odgers
Building production AI systems — fine-tuned LLMs, RAG pipelines, and cloud-native inference platforms — with the infrastructure depth to ship them.
About
I'm a Junior AI Engineer at Odgers in London, building production AI systems including fine-tuned LLMs, RAG pipelines, full-stack AI applications, and cloud-native ML inference platforms. My background in enterprise infrastructure gives me a deployment edge most AI candidates lack.
Day-to-day I support a hybrid AWS/Azure/M365 environment for 800+ users across EMEA, APAC, and AMER — and I've shipped an LLM-based triage system at work that drove a ~35% efficiency improvement.
Currently pursuing an MSc in Artificial Intelligence at the University of Liverpool (2026–2028) and working towards AWS Machine Learning Associate certification.
Projects
Production AI systems, ML infrastructure, and full-stack applications — built end-to-end.
Full-stack personal finance app ingesting Monzo/Starling bank data via CSV with auto-categorisation across 20+ spending categories. Privacy-first architecture: raw transactions processed locally, only aggregated summaries sent to Claude Haiku for insight generation (~£0.11/user/month). Includes a compound growth simulator modelling opportunity cost of spending over 1–30 year horizons.
Fine-tuned Qwen2.5-0.5B-Instruct using LoRA adapters on ~800 synthetic samples for structured IT ticket classification. Deployed as a FastAPI microservice achieving ~95% schema-valid JSON output compliance. Born from a real operational bottleneck at Odgers — the production version drove a ~35% improvement in ticket handling efficiency.
A retrieval-augmented generation backend built on 384-dim SentenceTransformer embeddings, IVFFlat-indexed pgvector store, and cosine similarity top-k retrieval hitting sub-100ms latency. Fully documented REST API with typed request/response contracts, ready to be dropped behind any LLM front-end.
Production ML inference API on AWS ECS Fargate behind an ALB, with full infrastructure-as-code via Terraform and a CI/CD pipeline through GitHub Actions using AWS OIDC keyless auth. Designed for zero-downtime deployments with automatic container image promotion through ECR.
Skills
The tools and technologies I work with.
AI / ML
Backend & APIs
Cloud & Identity
Currently studying
Contact
Open to new opportunities, collaborations, and interesting conversations. Drop me a line.
contact@raian.uk