Junior Software Engineer

JR United Kingdom; Exeter; On-site; GBP 35,000 - 55,000; Full time

Job summary

A fast-growing AI start-up in Exeter seeks a developer passionate about AI solutions. Work entails collaborating on projects involving Large Language Models (LLMs) and software development while ensuring high code quality and agile methodologies. Ideal for candidates with a background in STEM and experience with cloud technologies and AI frameworks.

Benefits

Healthcare insurance upon passing probation

Qualifications

• Experience with LLM frameworks (Haystack, LlamaIndex, LangChain).
• Agile framework experience is preferable.
• Building production-grade ETL pipelines and backend web development.

Responsibilities

• Collaborate with the CTO and engineers on client projects and internal products.
• Develop event-driven and request-response systems for RAG.
• Optimize LLM inferences for AI solutions.

Skills

Python

C/C++

AWS

Git

Data Engineering

Communication

Education

BSc or MSc in Mathematics, Physics, Computer Science, or Engineering (STEM)

Tools

Docker

Kubernetes

Job description

Social network you want to login/join with:

Brainpool is a fast growing AI start-up, providing custom AI services for business since 2017. Brainpool network of 500 top-level AI and Machine Learning experts supporting delivery of our projects include PhD and MSc-level scientists from top universities such as UCL, Oxford, Cambridge and Harvard. Brainpool provides companies with end-to-end AI solutions, starting from strategy development, planning all the way to implementation.

This role will involve working alongside the CTO and a team of engineers, on various business engagements, such as client projects and internal company products. Some examples of these engagements include client scoping programmes, and PoC/MVP software development. A significant focus will be on building and optimizing Large Language Model (LLM) inferences and creating robust web services. This includes developing event-driven and request-response systems to run RAG (Retrieval-Augmented Generation) answer generation pipelines, essential for delivering sophisticated AI-driven solutions. Your role will require strong communication skills to effectively liaise between application and product development teams, as well as to articulate complex technical concepts at varying levels of detail. Your contributions will be pivotal in advancing the company's capabilities in LLM inferences and enhancing the overall quality of AI solutions.

Requirements

• Some experience in programming languages such as Python, C/C++, and familiarity with object-oriented programming.
• Experience of working with or an understanding of LLM frameworks such as Haystack, LlamaIndex, and LangChain, with a focus on Retrieval-Augmented Generation (RAG) and text/chat generators.
• Cloud computing with AWS (ECS, EKS, DynamoDB, Bedrock)
• Knowledge of git version control, branching, and code versioning.
• Passionate about code quality, adhering to best practices for code quality, performance, testing, monitoring, documentation, CI/CD.
• Experience working in an agile framework preferable, including defining functional and non-functional requirements and sprint tasks.
• Understanding of data engineering, some experience with building production-grade ETL pipelines, as well as backend web development, backend-for-frontend, GraphQL, and FastAPI.
• Strong communication skills, able to communicate with both technical and commercial people.
• BSc or a MSc in Mathematics, Physics, Computer Science, or an Engineering discipline (STEM).

Desirable knowledge and experience

• Understanding of or working with AI/ML algorithms and data science.
• Docker and Kubernetes.
• Experience with Large Language Model stacks, vector databases, Haystack, open-source (Mistral, Falcon, Llama 3), and closed-source models like GPT-4 and Claude.
• Knowledge of Git version control, branching, and code versioning.

Renumeration:

• Healthcare insurance upon passing probation