Senior Python Developer (AI Integration)

Zagreb (Remote), Croatia (Hybrid)Remotesenior

Software EngineeringPython Developer

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

ROKO Labs is looking for a Senior Python Engineer with deep AI expertise to join our team working on large-scale, production-grade intelligent systems.

Key Responsibilities

Architect and develop scalable, production-grade Python applications, including LLM-powered systems, RESTful APIs, and microservices using FastAPI, Flask, or Django Design and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines,…

Requirements Summary

7+ years of software development experience, with the latest 1–2 years focused on AI/LLM-powered solutions Strong, expert-level Python skills — Python is the primary language for this role Proven hands-on experience building and deploying LLM…

Technical Tools

anthropicawsazuredjangodockerdynamodbfastapiflaskgcphuggingfacekafkakubernetesmongodbmysqlnumpyopenaipandaspostgresqlpythonscikit-learnsqlworkdayb2bmicroservicesrest-apissystem-design

ROKO Labs is looking for a Senior Python Engineer with deep AI expertise to join our team working on large-scale, production-grade intelligent systems. If you love writing clean, well-tested Python code, thrive in cross-functional environments, and are excited about building real-world AI solutions — come join a team of like-minded, caring professionals.

About the Role

~1 min read

You will be a core technical contributor on complex AI-powered projects, combining strong Python engineering fundamentals with hands-on experience in modern AI/ML technologies. You'll work closely with Product Owners, customers, engineering, and data teams to translate requirements into robust, scalable systems — and take real ownership of technical decisions.

Responsibilities

~1 min read

→Architect and develop scalable, production-grade Python applications, including LLM-powered systems, RESTful APIs, and microservices using FastAPI, Flask, or Django

→
Design and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, embedding workflows, and semantic search solutions in Python

→
Build, optimize, and maintain data ingestion pipelines and background task processing using Celery, RabbitMQ, or Kafka

→
Integrate and manage LLM APIs and AI platforms (e.g., OpenAI, Anthropic, Azure OpenAI) within robust Python service architectures

→
Design and optimize database schemas and queries across relational (PostgreSQL, MySQL) and NoSQL (MongoDB, DynamoDB) databases

→
Design scalable vector database architectures (e.g., Pinecone, Weaviate) to support AI-driven search and retrieval features

→
Containerize and orchestrate Python services using Docker and Kubernetes for reliable, repeatable cloud deployments (AWS, Azure, or GCP)

→
Identify and resolve performance bottlenecks in Python applications through profiling, caching strategies, and code optimization

Requirements

~1 min read

7+ years of software development experience, with the latest 1–2 years focused on AI/LLM-powered solutions
Strong, expert-level Python skills — Python is the primary language for this role
Proven hands-on experience building and deploying LLM applications, especially RAG-based systems
Good knowledge of Python web frameworks and libraries: Django, Flask, FastAPI
Experience with data-processing libraries: Pandas, NumPy, Scikit-learn
Solid understanding of vector databases (e.g., Pinecone, Weaviate) and semantic search architectures
Experience integrating LLM APIs (OpenAI, Anthropic, Azure OpenAI)
Strong understanding of RESTful APIs, microservices, and scalable backend architecture
Good working knowledge of cloud platforms: AWS, Azure, or GCP
Solid experience with SQL and relational databases (PostgreSQL, MySQL)
Experience with messaging queues (RabbitMQ, Kafka) and Docker
Experience with NoSQL databases (MongoDB, DynamoDB) — a plus
Strong testing, debugging, and problem-solving skills
Strong communication skills; Intermediate English or higher
BSc/MSc in Computer Science, Engineering, AI, or a related field

Nice to Have

~1 min read

Experience with multi-agent AI system design
Familiarity with alternative vector databases (FAISS, Milvus)
Experience with the Hugging Face ecosystem or fine-tuning open-source models
Hands-on experience with advanced MLOps frameworks and model governance
Experience with system architecture or leading a software team
PhD (completed or in progress) in a relevant field

What We Offer

~2 min read

✓Our developers work on only one project at a time, so there is no need to juggle 2 or more project

✓We work on long-term projects, you have the opportunity to get to know the client and his needs well, as well as the team

✓You will have the opportunity to work on complex solutions with the latest technologies

✓Remote work means it's up to you whether you work from home, beach, or the office

✓Flexible working hours mean that you can tailor your workday to your preferences, without a time-tracking system

✓All our employees will right away receive a contract for an indefinite period (B2B collaboration is also an option)

✓We provide regular feedback as part of our commitment to your ongoing development and success

✓Job role switch, if you want to try some new roles or technologies, we are here to support you by providing opportunities, feedback, and mentor

✓If you love taking courses or going to conferences, we are always open to discussing education opportunities

✓Each team has its own monthly knowledge-sharing sessions combined with weekly talks and brainstorming sessions aimed at improving our current work and processes

✓If you have a colleague or a friend who could be a good fit for us, we can offer you a referral fee

✓Salary will be based on your experience and skills