Software Engineer 2 (Python)

Allegro focuses on delivering core search and retrieval capabilities for the Allegro AI Assistant, maintaining a critical entry point for users to discover products, compare offers, and get personalized recommendations through natural conversations. The system combines modern microservice architecture with Large Language Models, high-performance retrievers, and vast data sources, emphasizing data quality, robust context building, and near real-time accuracy.

• Code in Python, Java, and Kotlin.
• Creative approach to search experience challenges.
• Ability to create solid code, accept comments, and share knowledge during code reviews.
• Ability to find effective solutions to user requirements.
• Commitment to continuous development and knowledge updating.
• English proficiency at least B2 level.

Nice to have:

• Openness to diverse technologies and workflows, including dev-operational tools and working with data.
• Basic experience with LLM tuning (LoRA, PEFT), training and evaluation pipelines for models.
• Experience with frameworks for building AI Agents (Agent Development Kit, LangChain, AutoGen, CrewAI).

Performance & Scale:

• Design, build, and optimize AI-driven systems that process complex natural language interactions.
• Deliver low-latency, high-quality responses from the AI Assistant with high availability and smart optimization of LLM and retrieval workloads.

Modern Tech Stack:

• Work with a cloud-native polyglot environment using Java, Kotlin, Spring, and ADK for backend.
• Utilize Python and LangChain for complex LLM orchestration.
• Use Langfuse for observability, prompt tracking, and evaluation.
• Leverage advanced vector search and modern ML solutions.

True Ownership & Autonomy:

• Join an agile, autonomous team with full ownership of AI microservices and data pipelines from design to deployment.
• Implement improvements based on experiments and AI evaluation metrics.

Complex Challenges:

• Work on LLM orchestration, Retrieval-Augmented Generation (RAG), and semantic search optimization.
• Integrate advanced embedding models, prompt pipelines, and vector databases to ensure accurate information retrieval.