AI Engineer

• Lead the integration of cutting-edge language technologies into real-world applications
• Collaborate cross-functionally with software engineers, DevOps, and product teams
• Build and deploy rapid prototypes and MVPs
• Design and optimize prompts for various LLM use cases
• Implement evaluation metrics for models, including perplexity and user satisfaction
• Monitor production systems for drift detection and performance degradation
• Automate metric tracking via MLflow or custom dashboards
• Conduct A/B testing for evaluating GenAI features in production environments

Technologies:

• AI
• API
• Azure
• DevOps
• FastAPI
• Flask
• Git
• GitHub
• LLM
• Python
• SQL
• numpy
• pandas
• Cloud
• Support
• Marketing

• Proficiency in Python Programming
• Strong focus on GenAI and LLMs
• Experience in Data Handling with NumPy, Pandas, and SQL
• Proficient in Git/GitHub for version control
• Familiarity with system integration and deployment
• Experience with model deployment using Flask, FastAPI, or MLflow
• Knowledge of model serving tools like Triton Inference Server and Hugging Face Inference Endpoints
• API integration experience with OpenAI, Anthropic, Cohere, or Mistral APIs
• Understanding of LLM frameworks like LangChain and LlamaIndex
• Familiarity with vector databases such as FAISS, Weaviate, Pinecone, Qdrant (Nice-to-Have)
• Experience in building hybrid systems combining LLMs with enterprise data
• Knowledge of MLOps practices including model versioning, monitoring, and logging
• Skills in bias detection and mitigation
• Experience in content filtering and moderation
• Understanding of explainability and transparency in AI
• Familiarity with LLM safety and guardrails
• Experience with Azure Cloud