Location: Hybrid (London Office)
Salary: Aligned with London AI/ML market rates
About Us
We are an AI-powered consumer intelligence company transforming qualitative research through cutting-edge automated moderation and real-time insight generation. Our platform is powered by advanced Large Language Models (LLMs), GenAI-driven analytics, and a modern cloud data ecosystem across AWS, Azure, and MongoDB. As we expand our GenAI capabilities, we are seeking an AI Specialist who blends deep LLM expertise with strong data engineering fundamentals. This role is ideal for someone who excels at building intelligent model behaviours and the data pipelines that support them.
The Role
You will design, refine, and productionise the AI systems that power our platform — from AI moderators and synthetic respondents to automated insight-generation models and evaluation frameworks. This is a hybrid role combining LLM development, finetuning, and AI evaluation with data engineering, cloud infrastructure, and lakehouse architecture.
What You’ll Do
LLM & GenAI Design + Finetuning
- Design prompts, reasoning flows, and intelligent behaviours for AI moderators and synthetic respondents.
- Fine-tune LLMs using curated datasets (LoRA/QLoRA, supervised finetuning, RLHF-style workflows.
- Prototype new GenAI features, including automated insight extraction, multi-turn conversation handling, and generative UX testing.
- Run structured experiments to optimise model performance, prompt strategies, hyperparameters, and inference configurations.
Data Engineering & Cloud Systems
- Build and maintain scalable data pipelines for model training, evaluation, analytics, and production workflows.
- Work across AWS Athena, Glue, S3 and Azure equivalents to support a lakehouse architecture.
- Use MongoDB effectively with strong schema design, indexing, and aggregation pipeline skills.
- Develop dbt models and SQL transformations for clean, reproducible datasets powering GenAI models.
- Build embedding pipelines, feature stores, and datasets for finetuning, retrieval, and evaluation.
- Ensure high-quality ETL/ELT workflows across AWS, Azure, and MongoDB environments.
Evaluation & Quality Systems
- Develop automated evaluation frameworks to measure LLM quality, accuracy, hallucinations, tone, and behavioural consistency.
- Build benchmark datasets and test suites for conversation quality, insight accuracy, and model reliability.
- Diagnose model failure modes such as drift, behaviour degradation, repetition loops, or hallucination patterns.
- Implement human-in-the-loop evaluation workflows for calibration and continuous improvement.
Cross-Functional Collaboration
- Work with engineering to deploy LLM-driven features and integrate evaluation into CI/CD pipelines.
- lines.Partner with product and research teams to ensure AI behaviours align with qualitative research standards.
- Monitor model quality, data pipeline performance, and dataset integrity, driving iterative improvement.
Requirements
- 3+ years of experience in AI/ML engineering, LLM development, or applied data science.
- Hands-on experience finetuning LLMs (HuggingFace, LoRA/QLoRA, custom datasets,
- RLHF).Strong programming skills in Python and SQL.Solid experience with MongoDB including schema design, indexing, and aggregation pipelines.
- Experience with AWS (S3, Athena, Glue, Lambda, Step Functions) and Azure (ADLS, Data Factory, Azure ML).Understanding of data lakehouse architectures and modern data warehousing.
- Experience building dbt models and maintaining ETL/ELT workflows.
- Familiarity with embeddings, vector retrieval, evaluation frameworks, and model performance analysis.
- Experience building datasets and pipelines for LLM training, evaluation, or retrieval systems.
Bonus
- PointsExperience with RAG pipelines, vector databases (Pinecone, Weaviate, OpenSearch), or multi-agent orchestration.
- Experience building conversational agents or AI-driven automation systems.
- Knowledge of MLOps tooling such as SageMaker, MLflow, or Databricks.
- Familiarity with RLHF, alignment techniques, or model interpret ability.
- Interest in consumer behaviour, research methodologies, or product decision-making.
- Startup experience or comfort with high-velocity environments.
Why Work for Bolt Insight?
- Hybrid working — home or London office (UK work rights required).
- Private Medical Insurance via Vitality.
- Nest Pension contributions.
- Employee referral bonuses.
- Virtual and in-person team gatherings.
- Recognition awards for outstanding contributions.
- Annual bonus — up to two months’ salary based on company performance.
- A unique opportunity to shape the future of AI-driven qualitative research through advanced LLM and data engineering systems.
:quality(80))
:quality(80))
:quality(80))