#10752
nsibilities & deliverables:**
Design, develop, and deploy production-grade large language model systems across a wide variety of applications (e.g. RAG, text-to-SQL, specialized agents etc., summarization, etc.)
Architect and implement agent and multi-agent systems leveraging state-of-the-art LLM frameworks
Creation of tools and functions to enhance LLM capability
Establish and maintain model lifecycle management practices, including version control, evaluation metrics, and performance monitoring
Optimize LLM applications for production environments, balancing performance, cost, and latency requirements
Perform robust model validation and security assessments of LLM systems
Collaborate closely with product teams, data engineers, and software engineers to integrate LLM capabilities into products and services
Lead technical discussions and present complex AI concepts to both technical and non-technical stakeholders
Stay current with the rapidly evolving LLM landscape and implement best practices
Mentor junior data scientists and engineers across the organization in LLM development techniques
Required skills & experience:
5+ years of professional experience in data science or machine learning engineering
Proven experience developing and deploying production-grade large language model systems
Strong proficiency in Python and related data science/ML libraries
Experience with LLM frameworks such as LangGraph or similar orchestration tools
Practical knowledge of prompt engineering, fine-tuning, retrieval-augmented generation, text-to-sql, and other related LLM tasks
Experience implementing agent and multi-agent systems with LLMs
Strong knowledge of deploying LLM systems and agents in production environments
Strong understanding of model lifecycle management and monitoring practices
Familiarity with cloud environments (e.g. Azure, databricks) and MLOps best practices
Experience with distributed computing and handling large-scale data processing
Thorough understanding of security best practices around LLM systems
Excellent collaboration skills and experience working with cross-functional teams
Strong knowledge of software development best practices (version control, CI/CD, testing)
Exceptional leadership, communication, and presentation skills
Advanced degree (MS or PhD) in Computer Science, Machine Learning, or related technical field
Technical Skills:
Aside from Python and SQL, we do not require previous working experience with most of the other skills listed below.
Programming Languages: Python (required), SQL
ML/LLM Frameworks: LangChain, LangGraph, Hugging Face Transformers, PyTorch, TensorFlow, or equivalent
Vector Databases: Pinecone, Weaviate, Milvus, Qdrant, or similar
Cloud Platforms: Azure, Databricks, AWS, or equivalent
MLOps Tools: MLflow, Weights & Biases, Kubeflow, or similar
Development Tools: Git, GitHub/GitLab, CI/CD pipelines
Data Processing: Pandas, PySpark, Dask, Spark, or equivalent
Containerization: Docker, Kubernetes
API Development: FastAPI, Flask, Langgraph Platform
Monitoring & Observability: Langsmith, Prometheus, Grafana, or similar
#LI-MG1