Data science & AI engineering consultant

I build useful products with data and AI.

I help teams turn messy data and half-working AI prototypes into reliable products that people can use.

Start with the work

I map the workflow before choosing models, vendors, or architecture.

Ship, then measure

I get useful pilots in front of users, then measure and improve them.

Stay understandable

Teams should know what the system does, where it fails, and which trade-offs they accept.

How I help

A practical mix of engineering, data, and strategy.

Most AI work fails in the handoff between idea, data, product, and production. I work across that handoff.

LLM Product Engineering

I design and ship LLM applications: RAG chatbots, knowledge assistants, and LLM eval suites tailored to your data and use case. Quick wins that move the needle, from early pilots to 10k-user rollouts.

What this can include
  • Retrieval pipelines (vector, hybrid, graph, search tuning from logs)
  • Evaluation frameworks (LangSmith, custom)
  • Indexing & enrichment workflows
  • Latency & cost optimisation on AWS / Azure

Data Science & MLOps

I turn messy data into structured, usable datasets and build semantic search and recommender systems on top, using LLMs for feature engineering, enrichment, and large-scale dataset creation.

What this can include
  • Data products from unstructured sources (tickets, logs, product feeds, documents)
  • LLM-powered labelling, feature engineering, and enrichment at scale
  • Semantic search and recommenders combining structured and unstructured data
  • ETL pipelines with CI/CD, tests, and drift / performance monitoring

AI Strategy & Advisory

I help teams pick the right AI bets, build a realistic roadmap, align stakeholders, and grow internal capability while staying close enough to the implementation to keep the advice honest.

What this can include
  • ROI and risk workshops grounded in your data and workflows
  • Use-case discovery and prioritisation (what to build first, what to skip)
  • Hiring and tech-stack decisions (build vs buy, vendor selection)
  • Mentoring internal engineers and product teams on shipping with LLMs
Selected work

A career across data, AI, and product.

I have worked across affiliate technology, retail, SaaS, and enterprise AI, usually in the messy middle between data science, product, and engineering.

Awin Global · Freelance · Oct 2024 to present

AI/ML Staff Engineer

Architecting and delivering production AI systems across RAG, agents, evaluation, and reusable platform capabilities.

More details
  • Built and evolved Awin's AI assistant with LangGraph and Deep Agent
  • Designed hybrid retrieval and semantic search on AWS and Azure
  • Built reusable evaluation workflows with CI gates, human review, LangSmith, and Langfuse
  • Shaped platform patterns for model access, observability, governance, cost tracking, and quotas
  • Supported recommender systems, classification, hiring, mentoring, and AI strategy

affiliate.ai · Freelance · May 2023 to Oct 2024

AI Engineer

Built an affiliate-marketing assistant delivered through Slack and Microsoft Teams.

More details
  • Implemented LLM features and function calling with LangChain
  • Designed RAG across SQL, APIs, and unstructured documents
  • Built evaluation workflows with LangSmith
  • Integrated Awin, Impact, CJ, Rakuten, and ShareASale data
  • Contributed to product decisions and AWS operations

SFEIR · Permanent · Dec 2021 to Apr 2023

Data Scientist and Consultant

Scoped and delivered data science projects for retail, then explored early generative AI use cases.

More details
  • Ran scoping workshops with business teams at Leroy Merlin
  • Built training, prediction, and evaluation pipelines
  • Deployed models in batch and real time
  • Designed business KPIs, monitoring, and dashboards
  • Benchmarked LLMs and prototyped semantic search over PDFs

Banque Populaire du Nord · Sep 2018 to Oct 2021

Data Scientist

Built customer analytics and NLP systems for relationship marketing and banking teams.

More details
  • Developed customer scores and segmentations from ideation through MLOps
  • Built an NLP backend for advisor-client reports and CRM follow-up
  • Created Power BI reporting for business users
  • Mentored an intern and shipped a recommendation API
  • Presented data work to business and technical communities
Field notes

Writing is part of the work.

I use the blog to think in public about LLM engineering, AI platforms, evaluation, and probabilistic software.

Browse all field notes
Proof of work

A few demos and references.

Practical walkthroughs and references that show how the systems behave.

“Othman is a first-class Data Scientist and engineering team member.

He has an excellent work ethic, and unwavering dedication to his colleagues and work.

I had the pleasure of working with him on a new generative AI solution designed to meet the needs of thousands of customers.

At the time of writing (March 2025), building generative AI applications can be highly complex, with a multitude of unknowns and unpredictable outcomes due to the probabilistic nature of generative AI models.

As a key member in our team, Othman designed and implemented our evaluations methodology and technology stack. His work has been invaluable to understanding the performance and optimization requirements for our solution. Beyond his technical expertise, Othman is a superb communicator, adept at speaking to counterparts at all levels in our organization, from the most technically proficient, to critical non-technical stakeholders.

I am well aware that Othman's skillsets extend far beyond the remit that we have worked together. Beyond the evaluations work, he also conducts deep quantitative analysis of unstructured data to obtain meaningful business insights.

I highly recommend Othman as an experienced and trusted colleague.”

James Bentley, AI Strategy Director, Awin Global

“Othman is in the top 1% of engineers and humans I have ever worked with. If you are lucky enough to have the opportunity to do so, work with Othman.”

About

A technical partner for the fuzzy middle.

I’m a freelance AI and data science consultant with eight years of experience across affiliate technology, retail, SaaS, and enterprise AI. I design and ship LLM products, data pipelines, and recommender systems end to end, from messy data to production.

I sit between strategy and engineering, helping teams choose the right AI bets and actually get them shipped.

A little human context

Off the keyboard, I’m a distance runner and philosophy-language nerd who loves quirky questions.

I like working with teams who want straight thinking, practical systems, and a light enough tone that the work stays fun.

Start a conversation

Have an AI system to clarify, rescue, or ship?

Bring the messy version. We can talk through the workflow, the data, the risks, and what a useful first step would look like.

Book a 15-min call