Data Scientist - NLP, LLMs, & Prompt Engineering

ZipRecruiter; London; Remote; GBP 90,000; Full time

Job summary

A leading company is seeking a Data Scientist specializing in GenAI, Python, and NLP for a remote contract role lasting 3-6 months. The ideal candidate will have expertise in prompt engineering and deploying NLP solutions, working with LLMs to enhance AI interactions. Responsibilities include developing intelligent conversational flows and collaborating with cross-functional teams to implement LLM features effectively.

Qualifications

• Proven experience with Python and NLP libraries.
• Hands-on experience with LLMs and prompt engineering.

Responsibilities

• Develop and deploy NLP solutions using libraries.
• Design and refine targeted prompts for AI chatbots.

Skills

Python

Natural Processing

Prompt Engineering

Tokenization

Context Management

Education

Linguistics

Cognitive Science

Human-Computer Interaction

Tools

NLTK

SpaCy

TextBlob

LangChain

LlamaIndex

Git

Job description

Job Description

Role: Data Scientist – GenAI, Python, NLP, LLMs, & Prompt Engineering

Location: Remote

Contract – 3-6 Months

Rate - £450/Day Outside IR35

Job Overview:

We are seeking a highly skilled and creative Data Scientist with deep expertise in Python programming, Natural Processing (NLP), and Large Models (LLMs). This role demands hands-on experience in prompt engineering, designing intelligent conversational flows, managing context windows, and interfacing with APIs such as OpenAI’s Chat Completions API. The ideal candidate should be capable of designing, evaluating, and optimizing AI systems that generate high-quality, context-aware responses.

Key Responsibilities:

• Develop and deploy NLP solutions using libraries such as NLTK, SpaCy, and TextBlob.
• Engineer prompts for LLMs using zero-shot, few-shot, chain-of-thought, and meta-prompting techniques.
• Design and refine targeted prompts to drive intelligent behavior in AI chatbots.
• Write Python functions to interface with APIs, especially OpenAI’s Chat Completions API and similar LLM platforms.
• Manage token economy and conversational context for long, multi-turn dialogues.
• Architect sequential, step-by-step task flows for complex LLM workflows.
• Evaluate and analyze AI-generated responses to iteratively improve prompt quality and outcome accuracy.
• Collaborate with product, design, and engineering teams to deploy and monitor LLM-based features.
• Conduct experiments and fine-tune prompts to enhance response relevance, coherence, and factual correctness.

Required Qualifications:

• Proven experience with Python and NLP libraries such as NLTK, SpaCy, TextBlob, or similar.
• Hands-on experience working with LLMs (e.g., OpenAI, Claude, Mistral, etc.).
• Deep understanding of prompt engineering strategies and conversational AI workflows.
• Experience building and consuming RESTful APIs.
• Strong grasp of tokenization, embedding-based memory, and context management in LLMs.
• Ability to evaluate AI outputs for quality, relevance, and consistency.
• Familiarity with version control systems (e.g., Git) and agile development practices.

Qualifications:

• Experience with LangChain, LlamaIndex, or other LLM orchestration tools.
• Background in linguistics, cognitive science, or human-computer interaction.
• Prior work in chatbot development, virtual assistants, or AI-driven user interfaces.
• Knowledge of RAG pipelines, vector databases, and semantic search.