Job Description:
Requirements:
• 4+ years of experience as a Python AI Engineer.
• Strong experience with FastAPI, SQLAlchemy, and PyTest.
• Experience with agentic AI frameworks (e.g., Haystack, Lang Graph, CrewAI).
• Familiarity with LLM-based systems and integration patterns.
• Working experience of Docker, Kubernetes, and Git.
• Hands-on experience with Azure cloud services (especially Azure AI, Azure Functions, etc.).
• Familiarity with Postgre
SQL.
• Experience with Retrieval-Augmented Generation (RAG), including vector databases and embeddings.
• Experience with Langfuse or similar LLM evaluation/monitoring tools.
• Experience with CI/CD workflows and observability tools.
• Interest in emerging LLM/agentic tooling and frameworks.
• Solid understanding of natural language processing techniques, with experience in deploying NLP systems and working with prompt libraries.
• Expertise in data analysis and analytics.
• Proven track record of driving innovation and solving complex technical problems using AI and machine learning.
• Good communication skills, with the ability to convey complex technical concepts to both technical and non-technical stakeholders.
• Experience working collaboratively within cross-functional teams.
• Understanding of data privacy and security standards, ensuring systems are compliant with industry regulations and best practices.
• Passion for continuous learning and staying updated with the latest trends and advancements in AI/ML technologies.Responsibilities:
• Collaborate with PO, BA, stakeholders to understand the specific needs and requirements of the business process.
• Translate business needs into technical specifications.
• Collaborate with frontend engineers, Data Scientists, and Dev Ops to deliver scalable LLM solutions.
• Develop and maintain backend services using FastAPI.
• Work with agentic AI frameworks like Haystack to build AI pipelines and components.
• Design and implement robust database models using SQLAlchemy with Postgre
SQL.
• Write and maintain unit and integration tests using PyTest.
• Deploy services using Docker and Kubernetes.
• Utilize Azure services (e.g., Azure AI) for hosting, inference, and other cloud-native features.
• Use Langfuse or similar tools for LLM performance monitoring and evaluation and implement improvements as necessary.
• Develop and refine the prompt library to facilitate seamless user interaction and request handling.
• Ensure the AI models integrate effectively with existing applications and workflows.
• Conduct thorough testing of AI models to ensure they meet quality, performance, and accuracy standards.
• Provide ongoing support and troubleshooting to address any system issues.
• Monitor and adapt AI systems to accommodate changes in the business process or user requirements.
• Create comprehensive documentation for developed solutions.
