Python Backend Developer (AI/LLM)

Job Description

// About EVA.ai

Basically, EVA.ai is what you see ATM 🙂 It’s an A to Z solution for searching and matching such great talent like you to the best jobs in the company, helping them with screening, interviews, etc.

• Our clients are as big and cool as the United Nations (yeah, that one) and growing.

• We’ve got an AI chatbot, AI Matching, AI Job Recommendation etc.

• We believe in agile, practice SCRUM, follow SOLID principles and love innovations.

• We don’t hire juniors, so we are quite smart and quite efficient 🙂

// Position Description

We are looking for a Python Backend Engineer to develop backend systems for LLM-based AI solutions. This role requires hands-on experience in Large Language Models (LLMs), API integrations, and scalable backend architectures.

As a Python Backend Engineer, you will be responsible for building and maintaining APIs, implementing Retrieval-Augmented Generation (RAG) and ensuring seamless AI system integration

This position is fully remote, so you can work from anywhere.

Responsibilities

• Build scalable backend architectures for AI-driven applications

• Integrate AI models with APIs, databases, and business applications

• Implement Retrieval-Augmented Generation (RAG)

• Work with SQL databases (PostgreSQL) to store and manage AI-related data

• Implement caching strategies and load balancing for efficient AI request handling

• Stay updated on the latest AI advancements and experiment with state-of-the-art techniques.

• Write code. SOLID practices, all sorts of tests, and pair reviews.

• Talk to people. We’re quite flat, so depends on the service and feature you will be working with product analysts, customer success, designers, and obviously other developers.

• Participate in SCRUM. Especially retros.

// Requirements

• Education: Bachelor’s degree in Computer Science or a related field (or equivalent experience)

• Language: English

• Python with experience in backend frameworks (FastAPI).

• Experience with LLM APIs (e.g., OpenAI, Mistral)

• Knowledge of Retrieval-Augmented Generation (RAG) and working with vector databases (e.g., Opensearch).

• Experience with cloud platforms (AWS) and containerization (Docker).

• Proficiency in database management (SQLAlchemy, PostgreSQL)

• Proficiency in LangChain for prompt chaining, memory handling, and tool integrations

• Experience designing and optimizing AI prompts

Plus but not a blocker will be:

• Experience with fine-tuning LLMs

• Experience with AI Agents and autonomous workflows

• Experience with microservices

• Experience with message queues (RabbitMQ)

• Experience with Redis for caching, session management

30 hours a week availability

// Compensation & Perks

• Competitive salary rate according to your level of experience (this vacancy is senior level).

• Fixed in local currency, USD or GBP

• Share options and bonuses available as you fit KPIs and stay with us for more than 1 year.

• You manage your time, it’s not required to be available all day.

• Learning courses/conferences sponsorship.

• You can work less than 40 hours a week.

Opportunities to grow

You discuss your individual growth plan with a CTO and put some KPIs on it.

Depending on your willingness, you can improve yourself:

Horizontal growth:

• Any optional technologies mentioned above;

• English;

• Chatbots;

• Security;

• AI;

• Data Analysis;

• Product Analysis;

• Customer Facing Activities;

Vertical growth:

• Architecture

• Ability to become Lead Developer after some time and take responsibility for 1 or more microservices

• Product owner of 1 or more services