We are seeking the expertise of an AI Engineer to build the intelligence layer of our client's platform. Systems/processes are recruitment practices, CV's, Documents, power intelligent automation within the healthcare industry.
Duties & Responsibilities
Build and operate Python AI/ML services that score and match workers to jobs and surface results into the product.
Design and implement best practices for production AI: evaluation harnesses, guardrails, monitoring, reproducibility and cost control.
Design and improve retrieval and matching pipelines: embeddings, vector search and taxonomy-driven scoring.
Integrate large language models for extraction, summarisation, classification and intelligent automation (use AWS Bedrock today, but you should be comfortable choosing and switching providers).
Build and train our own in-house models where they outperform or reduce reliance on third-party APIs: data preparation, training and fine-tuning, evaluation and deployment.
Own data quality for AI features, for example ensuring embedding and taxonomy data is correct so scores are meaningful rather than degenerate.
Partner with full stack engineers to expose AI capabilities through clean APIs, and with platform engineers on deployment and cost.
Monitor accuracy, latency and cost in production, and iterate based on real outcomes.
Desired Experience & Qualification
3 to 6 years building software, with strong, production-grade Python.
Hands-on experience building and shipping ML, NLP or LLM-powered features, not only research or notebooks.
The ability to design and implement best practices for AI systems: evaluation, guardrails, monitoring, reproducibility and cost control.
Practical understanding of embeddings, semantic / vector search and retrieval-augmented generation (RAG).
Experience integrating LLMs from any provider (for example Anthropic, OpenAI, AWS Bedrock or open models) into real applications.
The ability to build, train and fine-tune in-house models, not only consume third-party APIs: dataset preparation, training, evaluation and serving.
Comfortable building APIs and working with relational data (FastAPI and PostgreSQL; similar tools transfer well).
Solid grasp of prompt design, evaluation, and the failure modes of LLM and scoring systems, and able to reason about why a model behaves the way it does in production.
Nice to have
Familiarity with managed LLM platforms (for example AWS Bedrock), including model access, secure cross-account access and cost management.
Deep experience with model training frameworks (PyTorch, TensorFlow or Hugging Face) and serving custom models at scale.
Familiarity with vector databases / pgvector and building taxonomy or ontology-driven scoring.
Experience designing agentic systems, tool-use, or multi-step LLM workflows.
Workflow orchestration / automation tooling (for example Airflow, Prefect or similar).
MLOps experience: model/version tracking, evaluation harnesses, monitoring and observability for AI.
Comfort with containers, Kubernetes, and deploying Python services in production.
Background in matching, search, ranking, or recommendation systems.
Domain experience in healthcare, recruitment or HR-tech.
Desired Skills:
3 to 6 years building software with strong production-grade Python
Hands-on experience building and shipping ML
NLP or LLM-powered features
The ability to design and implement best practices for AI systems:
Domain experience in healthcare
recruitment or HR-tech.
Desired Work Experience:
5 to 10 years
Desired Qualification Level:
Degree