AI/LLM Engineer

RESPONSIBILITIES: 

Model Development & Deployment 

• Design, implement, and deploy LLM-powered applications from concept to production. 
• Build and maintain frameworks for prompt engineering, model evaluation, and workflow orchestration (e.g., Langflow, LangChain). 
• Ensure testing, validation, and quality control of generative AI models. 

Observability & Monitoring 

• Integrate Datadog or equivalent tools to monitor LLM applications for performance, reliability, and operational metrics. 
• Build dashboards and alerts to track model drift, performance anomalies, and GenAI metrics. 

Research & Continuous Improvement 

• Stay up-to-date with AI/ML techniques, frameworks, and libraries (Hugging Face, TensorFlow, PyTorch). 
• Identify opportunities to improve models, workflows, and automation practices. 

Collaboration & Engineering Excellence 

• Work closely with cross-functional teams to integrate LLM technologies into products and services. 
• Advocate for CI/CD, infrastructure as code, automated testing, and secure coding practices. 

REQUIREMENTS: 

• Strong hands-on experience in machine learning and GenAI, delivering production-ready solutions. 
• Deep expertise in LLM frameworks and orchestration tools: Langflow, LangChain, MLFlow, DeepEval. 
• Experience with Datadog LLM Observability or equivalent monitoring and tracing tools. 
• Proficiency in Python and object-oriented programming best practices. 
• Experience with deep learning frameworks: TensorFlow, PyTorch. 
• Familiarity with Hugging Face Transformers, Spacy, Pandas, and related AI/ML libraries. 
• Experience with Docker, Kubernetes, and cloud platforms (AWS, Azure, GCP). 
• Knowledge of Postgres, VectorDBs, and scalable data architectures. 
• Strong understanding of MLOps, CI/CD, and infrastructure as code. 
• Excellent problem-solving, communication, and collaboration skills. 
• English: Upper-Intermediate or higher