Job Description

The team waiting for you:

We’re forming a dedicated squad to take this from promising product to industry-leading platform. If you’re a Python developer who’s been itching to go deep on LLMs, RAG, and agentic AI — not just toy projects, but production systems at scale — this is your chance. You’ll work alongside experienced Staff Engineers, ship to real customers, and help define how AI reshapes B2B data intelligence. We have a seat ready for you!

In this role, you’ll:

• Design, develop, and maintain Python backend services powering our AI products.
• Build and optimize LLM-powered pipelines — RAG, semantic search, natural language query processing.
• Develop agent workflows and tool-use patterns for the AI Data Assistant.
• Integrate with large-scale data infrastructure — vector databases, search engines, and analytical query engines.
• Design and implement API endpoints to serve AI-generated insights to client-facing products.
• Optimize prompt engineering, LLM output quality, and system reliability.
• Collaborate with cross-functional teams (Data Engineering, API, Client Side) to deliver product features.
• Monitor and improve performance, latency, and cost efficiency of AI services.
• Contribute to evaluation frameworks and testing strategies for AI-powered features.
• Share knowledge and help build the team’s collective expertise in applied AI.

Your skills & experience:

• 2+ years of professional backend development experience.
• Experience building and deploying production-grade APIs.
• Familiarity with LLM APIs (OpenAI, Anthropic, or similar) — professional or personal projects.
• Understanding of retrieval-augmented generation (RAG) patterns or strong willingness to learn.
• Experience working with databases — relational (PostgreSQL/MySQL) and/or search engines (Elasticsearch).
• Experience with Docker and containerized environments.
• Strong problem-solving skills and genuine curiosity about AI technologies.
• Ability to work with ambiguity and evolving requirements in a fast-moving product space.

Nice to have:

• Experience with vector databases (Qdrant, Pinecone, Weaviate).
• Experience with LLM orchestration frameworks (LangChain, LlamaIndex).
• Experience with agent/tool-use patterns and agentic programming.
• Data engineering background — Kafka, Spark, Trino, dbt, or similar.
• Experience with prompt engineering and LLM evaluation.
• Experience with Kubernetes.
• Familiarity with observability tools (Grafana, Sentry, OTel).
• Understanding of NLP concepts (embeddings, semantic similarity, tokenization).