Tech Stack
AzureCloudDockerJavaScriptKubernetes.NETNext.jsPythonReactRedisSQL
About the role
- Lead and mentor a team of AI/ML engineers, fostering growth and technical excellence.
- Define and enforce coding standards, architectural patterns, and best practices.
- Collaborate with stakeholders to translate business needs into AI-driven solutions.
- Manage project timelines, technical risks, and team deliverables.
- Guide end-to-end lifecycle of Generative AI applications, ensuring technical excellence and scalability.
- Integrate and optimize applications using LLM provider APIs (OpenAI, Anthropic, etc.).
- Design prompts with advanced techniques (few-shot, chain-of-thought, chaining, context crafting) and implement safeguards.
- Build scalable backend services in .NET (C#) and Python, working with SQL and APIs.
- Develop and manage RAG pipelines, conversational AI systems, and summarization tools.
- Drive observability: tracing, logging, monitoring for LLM-powered systems.
- Benchmark and evaluate LLMs using custom datasets and automated testing; oversee reliability and performance tuning.
- Ensure solutions meet enterprise-grade standards for security and scalability.
Requirements
- 5+ years of professional experience in Machine Learning / AI engineering.
- 1–2+ years hands-on experience in Generative AI application development.
- Proven leadership or team lead experience (mentoring, managing, or leading AI/ML engineers).
- Strong backend engineering skills in Python.
- Solid knowledge of LLM providers (OpenAI, Anthropic, etc.) and prompt engineering techniques.
- Experience with RAG pipelines, AI workflows, and productionizing LLM systems.
- Hands-on with Docker, Kubernetes, REST APIs, and Azure (AKS, ACR, containerized deployments).
- Excellent communication skills (English, written and spoken).
- Preferred: Azure AI ecosystem (OpenAI, PromptFlow, Azure ML, AI Services), CosmosDB, KQL, Azure Log Analytics, App Insights.
- Preferred: Experience with multiple LLM providers (Anthropic, Mistral, Cohere, etc.).
- Preferred: Prompt caching, compression, and output validation strategies; Redis caching for performance optimization.
- Preferred: Frontend experience with React and Next.js.