Design, develop, and debug Python-based AI applications utilizing large language models and modern AI frameworks

Engineer effective prompts, workflows, and evaluation methods to optimize LLM performance across diverse use cases

Build and maintain REST APIs and integrate AI functionalities into scalable, production-grade systems

Research, experiment with, and evaluate emerging AI tools, frameworks, and methodologies to support solution design

Collaborate in an agile, cross-functional environment, delivering high-quality outputs under tight timelines

Stay current with rapid advancements in AI/LLM technologies and proactively apply new techniques

Support internal and external AI initiatives such as chatbot assistants, automation solutions, and intelligent features

Operate autonomously with strong ownership of deliverables, ensuring effective communication and alignment with US-based teams

Hands-on experience in Python application development and debugging with 2+ years

Strong expertise in prompt engineering and LLM behavior tuning

Deep knowledge of large language model architectures and appropriate use cases

Proficiency with Pydantic for data validation and settings management

Practical experience with AI orchestration frameworks such as LangChain or CrewAI

Familiarity with AI-powered engineering assistants like GitHub Copilot, Claude Code, or Gemini CLI

Experience working with AWS cloud services and infrastructure components

Experience with workflow automation platforms such as n8n, Make, or Zapier

Strong problem-solving skills

Excellent communication and collaboration skills

Ability to work autonomously and manage deliverables effectively

English language proficiency B2 (Upper-Intermediate) or higher

Experience with Gemini platform

Knowledge of CrewAI framework

Familiarity with automation solutions integration

Prior work with US-based client teams

Understanding of AI agent development methodologies