Middle Python Engineer

Summary

Join airSlate's GenAI team as an AI Engineer and contribute to the development of agentic AI implementations for product features and the core marketing engine platform. You will work on various aspects of Large Language Models (LLMs), including prompt engineering, retrieval-augmented generation (RAG), and fine-tuning. The role involves designing, implementing, and optimizing APIs and microservices, working with diverse database systems, and collaborating on improving engineering standards and processes. You will leverage extensive natural language datasets and cutting-edge LLM technologies. This position offers opportunities to work on advanced enterprise applications of LLMs and contribute to the next chapter of airSlate's growth.

Requirements

• Proficiency in Python and experience with modern frameworks (FastAPI, Flask, Django)
• Experience with tools and best practices in the Python ecosystem (Poetry, virtual environments, dependency management)
• Experience with LLM-based solutions, including prompt engineering, retrieval strategies, and evaluation
• Solid understanding of data design and database management (SQL, NoSQL, VectorDB)
• Experience designing scalable RESTful APIs and working with asynchronous programming (asyncio, FastAPI, Celery)
• Hands-on experience with RAG (Retrieval-Augmented Generation) and search pipelines
• Knowledge of message queue brokers (RabbitMQ, Kafka, Redis Streams)
• Experience with Git, GitHub, and CI/CD tools for automated testing and deployment
• Proficiency in cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes)
• High level of self-awareness, problem-solving, and proactivity

Responsibilities

• Develop and maintain AI-driven applications leveraging LLMs, RAG (Retrieval-Augmented Generation), and AI agent frameworks
• Design, implement, and optimize APIs and microservices, ensuring scalability and performance
• Work with various database systems, including relational, NoSQL, and vector databases
• Integrate and optimize message queue brokers for distributed system architectures
• Collaborate on prompt engineering, evaluation strategies, and fine-tuning LLM-based applications
• Build and maintain cloud-native applications using AWS and containerization tools
• Design and build new services from scratch for AI agents ecosystem
• Improve engineering standards, tooling, and processes
• Actively participate in code reviews
• Increase system’s performance and scalability
• Implement integrations with other products APIs

Preferred Qualifications

• Familiarity with LangChain, LangGraph, or other AI agent orchestration frameworks
• Hands-on experience with search and retrieval systems (Elasticsearch, Weaviate, FAISS, Vespa)
• Understanding of ML Ops practices (model deployment, monitoring, scaling)
• Experience optimizing LLM inference performance (quantization, distillation, caching)
• Exposure to NLP frameworks (Hugging Face, spaCy, NLTK, OpenAI APIs)
• Knowledge of workflow orchestration tools (Kubeflow, Airflow, Prefect) for AI pipelines
• Experience with data pipelines and feature stores (Kafka, DVC, Feast)
• Understanding of security & compliance requirements for AI applications (data privacy, access control)
• Familiarity with knowledge graphs and reasoning engines (Neo4j, RDF, SPARQL)

Benefits

• Flexible work environment — We value the advantages of in-person collaboration and prioritize work from our offices in Wroclaw or Bialystok. However, we also provide flexible work arrangements to accommodate remote or hybrid options and flexible scheduling
• Bonuses and compensation — On top of a competitive base salary, we reward our team members' performance with a quarterly bonus to recognize achievements, time, and effort
• Stock options — At airSlate, our team members are more than employees; they're business partners. We issue stock options that grant ownership in the company, allowing everyone to share in its growth
• Professional growth opportunities — We are committed to ongoing improvement and welcome those passionate about learning. We cover professional development courses, conferences, literature, English classes, and more for each team member
• Health and well-being —We prioritize the health and well-being of our team. This is why we provide a Luxmed subscription, a Multisport card for every team member, access to the office's massage room, free lunches, and healthy in-office snacks to sustain your energy. Also, we provide all our team members with Mental Health Days, dedicated days off recognized globally to encourage people to log off and recharge