Drive AI innovation by leading and implementing AI automation initiatives, including customer service case routing and internal workflow optimization using LLMs (GPT-4, Claude, Mistral), LangChain, AutoGen, and CrewAI., Solve high-impact problems independently, developing AI-native applications and deploying LLM-based architectures with FastAPI, Python, and cloud-based deployments (AWS/GCP/Azure) to significantly reduce engineering time and effort., Lead AI-powered automation efforts, integrating LLMs with external APIs (OpenAI, Anthropic, Hugging Face), databases (PostgreSQL, Pinecone, Weaviate, ChromaDB), and business logic to improve operational efficiency., Develop scalable and cost-efficient AI systems, optimizing LLM inference pipelines with vLLM, DeepSpeed, LoRA, and FSDP, and implementing best practices for AI observability, safety, and monitoring (Guardrails AI, Prometheus, Grafana, LangSmith)., Foster collaboration and AI adoption, working closely with the CTO, senior engineers, data scientists, and process managers to ensure AI solutions align with business objectives and integrate seamlessly into MLOps pipelines (Kubernetes, Ray Serve, BentoML, CI/CD workflows).
