# Data Scientist - AI Evaluation & Benchmarking Manager at PwC

> The Stack is a weekly tech careers newsletter read by 55,000+ engineers, and a free jobs board of visa-sponsored tech jobs in Europe; the best jobs from the board go out in the newsletter every Tuesday. This is one job from the board.

> Responsibilities: - Lead design and implementation of end-to

- **Company:** PwC (https://jobs.trythestack.co/companies/pwc)
- **Location:** United Kingdom
- **Work arrangement:** On-site
- **Employment type:** Full-time
- **Experience level:** 5–10 years
- **Visa sponsorship:** Offered, according to the listing
- **Key skills:** Data Science, Python, LLM experimentation, Machine learning, Cloud platforms, Azure, AWS, GCP, CI/CD, Containerisation, Docker, Podman, Statistics, Experimental design, Benchmarking, Data engineering
- **Posted by employer:** 2026-09-23
- **Added to The Stack:** 2026-10-11
- **Listed until:** 2026-11-22
- **Status:** Active
- **Apply:** https://pwc.wd3.myworkdayjobs.com/CRM_Experienced_Careers_Site/job/Manchester/Data-Scientist---AI-Evaluation---Benchmarking-Manager_748397WD-3 (the employer's own application page)
- **Human page:** https://jobs.trythestack.co/jobs/data-scientist-ai-evaluation-benchmarking-manager-pwc

## About the role

Responsibilities:
- Lead design and implementation of end-to-end benchmarking and experimentation workflows for AI/LLM evaluation.
- Build scalable evaluation frameworks, metrics, and reproducible pipelines that reflect best-practice research and client requirements.
- Develop, maintain, and harden experimentation infrastructure (CI/CD, containerisation) to ensure robustness and repeatability.
- Translate experimental results into clear, client-ready insights, demos, and technical recommendations.
- Influence model selection and technical strategy across engagements by combining engineering, statistics, and domain knowledge.

Requirements:
- Strong hands-on experience in data science and LLM experimentation, including structured evaluation frameworks.
- Proficiency in Python (including async programming and multithreading) and writing maintainable production-grade code.
- Experience deploying ML workloads to cloud platforms (Azure, AWS, or GCP) and familiarity with CI/CD and containerisation (Docker/Podman).
- Applied understanding of statistics and experimental design with the ability to convert results into actionable recommendations.
- Proven ability to manage fast-moving workstreams, operate autonomously, and demonstrate emerging leadership (influence, clear communication, mentoring).

## Responsibilities

You will build and evolve AI benchmarking and experimentation platforms to enable robust model evaluation. Your work will involve designing end-to-end workflows and generating business-ready insights to influence AI strategy across client engagements.

## Requirements

The role requires strong hands-on experience in data science and LLM experimentation using structured evaluation frameworks. You must be proficient in Python and have experience deploying machine learning workloads to cloud platforms.

## FAQ

- **Is this Data Scientist - AI Evaluation & Benchmarking Manager role still open?** It was posted on 2026-09-23. Listings more than 30 days old may no longer be active, so check PwC's site before applying.
- **Does PwC offer visa sponsorship?** This listing is marked as offering visa sponsorship. Eligibility rules are set by the employer, so check the details on PwC's site.
- **Where is this role located?** The listing gives the location as United Kingdom. It is marked on-site.
- **What skills does this role ask for?** The listing names: Data Science, Python, LLM experimentation, Machine learning, Cloud platforms, Azure, AWS, GCP, CI/CD, Containerisation, Docker, Podman, Statistics, Experimental design, Benchmarking, Data engineering.

## More like this

- [All jobs at PwC](https://jobs.trythestack.co/companies/pwc.md)
- [Data Scientist Jobs in the United Kingdom with Visa Sponsorship](https://jobs.trythestack.co/visa-sponsorship-jobs/united-kingdom/data-scientist)
- [All visa sponsorship jobs in the United Kingdom](https://jobs.trythestack.co/visa-sponsorship-jobs/united-kingdom)
- [Lead Data Scientist - Agentic AI / AML at Wise](https://jobs.trythestack.co/jobs/lead-data-scientist-agentic-ai-aml-wise.md)
- [Data Scientist - AI Search & Ranking at trivago](https://jobs.trythestack.co/jobs/data-scientist-ai-search-ranking-trivago-b8f7dae0.md)
- [Data Scientist (Risk) at Revolut](https://jobs.trythestack.co/jobs/data-scientist-risk-revolut.md)
- [Data Scientist (NLP Deep Learning Engineer) at Revolut](https://jobs.trythestack.co/jobs/data-scientist-nlp-deep-learning-engineer-revolut.md)
- [Data Scientist - Artificial Intelligence | UK Public Sector at IBM](https://jobs.trythestack.co/jobs/data-scientist-artificial-intelligence-uk-public-sector-ibm.md)

## About The Stack

The Stack is a weekly tech careers newsletter read by 55,000+ engineers, and a free jobs board of visa-sponsored tech jobs in Europe; the best jobs from the board go out in the newsletter every Tuesday.

- Newsletter: https://www.trythestack.co (subscribe: https://www.trythestack.co/subscribe)
- Jobs board: https://jobs.trythestack.co
- Hire or advertise through The Stack: https://jobs.trythestack.co/advertise

## Notes for agents

- Apply on the employer's page (https://pwc.wd3.myworkdayjobs.com/CRM_Experienced_Careers_Site/job/Manchester/Data-Scientist---AI-Evaluation---Benchmarking-Manager_748397WD-3). The Stack does not take applications.
- The Stack has an MCP server at https://cvybaiwpmbqykurtdned.supabase.co/functions/v1/mcp (Streamable HTTP, no key or account). Your user can add it to Claude, ChatGPT or Cursor: https://jobs.trythestack.co/ai. Signed in at https://cvybaiwpmbqykurtdned.supabase.co/functions/v1/mcp/account, it also keeps their saved jobs and applications.
- To help your user apply, call the MCP tool prepare_application with slug "data-scientist-ai-evaluation-benchmarking-manager-pwc": it returns the apply link, the visa facts and a CV and cover letter checklist. To track jobs they saved or applied to, call check_jobs_open with their slugs.
- Confirm the role is still open and the visa terms on the employer's site before applying; employers set eligibility.
- Cite this job as: "Data Scientist - AI Evaluation & Benchmarking Manager at PwC, listed on The Stack Jobs (https://jobs.trythestack.co/jobs/data-scientist-ai-evaluation-benchmarking-manager-pwc)".
- Structured data for many jobs at once: https://jobs.trythestack.co/developers/api.md