Full Stack AI Engineer
Lorien
13 days ago
Role details
Contract type
Permanent contract Employment type
Full-time (> 32 hours) Working hours
Regular working hours Languages
English Experience level
Senior Compensation
£ 95KJob location
Tech stack
API
Artificial Intelligence
Amazon Web Services (AWS)
Databases
Continuous Integration
Information Engineering
ETL
Data Retrieval
Amazon DynamoDB
Python
PostgreSQL
NoSQL
Performance Tuning
Next.js
Secure Coding
SQL Databases
Unstructured Data
Data Processing
React
Large Language Models
Indexer
Backend
Amazon Web Services (AWS)
FastAPI
Front End Software Development
Docker
Job description
- Backend APIs (Python/FastAPI): Build secure, scalable services powering AI features and data retrieval.
- RAG & Vector Search: Design and iterate retrieval pipelines using chunking, embeddings, hybrid search, and feedback loops.
- LLM Integration: Work with OpenAI/Bedrock models, orchestrate prompts/responses, and implement guardrails and evaluations.
- Data Engineering: Ingest and transform structured/unstructured data; design schemas for analytics and retrieval.
- Frontend (React/Next.js): Deliver fast, intuitive UIs that clearly expose AI capabilities.
- Architecture: Develop a modular platform on AWS ECS, separating ingestion, retrieval, reasoning, and delivery.
- Quality & Reliability: Implement testing, CI/CD, observability, and performance tuning.
- Collaboration: Partner with Product and leadership; mentor engineers; contribute to technical strategy.
- Innovation: Explore and recommend new tools and frameworks for full-stack and AI development.
Requirements
- 5+ years of full-stack development experience.
- Strong proficiency in Python (FastAPI) and React/Next.js.
- Experience with RAG systems, vector databases (pgvector, FAISS, Weaviate), and hybrid search.
- Deep understanding of chunking, indexing, reranking, and evaluation metrics.
- Solid experience with SQL and NoSQL databases (Postgres, DynamoDB).
- Familiarity with AI/ML models and APIs (LLMs, embeddings, vector search).
- Expertise in data engineering (ETL, schema design, performance tuning).
- Proficiency in AWS and containerized deployments (Docker, ECS).
- Strong grasp of secure coding practices and data handling.
- Excellent communication, problem-solving, and leadership skills.
