Python Engineer with GenAI knowledge

We’re looking for an experienced Python Engineer with hands-on expertise in building AI agents, developing robust APIs, and integrating Large Language Models (LLMs). You'll join a forward-thinking team working at the intersection of artificial intelligence and modern web technology.

Responsibilities:

• Develop and integrate AI agents using frameworks like Langchain, PydanticAI, or similar
• Build and maintain RESTful APIs using Django or similar MVC frameworks
• Work with vector databases (e.g., Weaviate, Pinecone, FAISS) for semantic search
• Work with relational databases (e.g., PostgreSQL, MySQL)
• (Bonus) Configure and run LLMs locally (e.g., LLaMA, Mistral, GPT4All)

Requirements:

• 3+ years of commercial Python development experience
• Hands-on experience with AI agents or LLM-based applications
• Solid knowledge of PydanticAI, Langchain, Google ADK or similar Hands frameworks
• Experience with both vector and relational databases
• Experience with web API development using MVC frameworks such as Django
• Hands-on experience with vector and relational DBs
• Understanding of LLM infrastructure concepts
• English proficiency for reading documentation and participating in calls

Nice to Have:

• Experience running open-source LLMs locally
• Familiarity with Docker and/or Kubernetes
• Background in Machine Learning or Natural Language Processing