Senior Staff Engineer, Generative AI

This is a fully remote position, open to applicants in Pennsylvania.

📋 Description

• Comprehend client business use cases and technical specifications, transforming them into technical designs.

• Align decisions with requirements and convey them to developers.

• Explore alternative solutions and determine the optimal choice to meet client needs.

• Establish guidelines and benchmarks for non-functional requirements throughout project execution.

• Draft and evaluate design documents that articulate application architecture, frameworks, and high-level design.

• Assess architecture and design for extensibility, scalability, security, design patterns, user experience, and non-functional criteria.

• Create and design comprehensive solutions for both functional and non-functional requirements.

• Identify technologies, patterns, and frameworks necessary to realize solutions.

• Grasp technology integration scenarios and apply insights within projects.

• Address code and review challenges through systematic root-cause analysis and substantiate decisions.

• Conduct proofs of concept to validate suggested designs and technologies.

⛳️ Requirements

• A minimum of 8 years of total experience.

• Profound knowledge of LLMs and Transformer architectures, including GPTs, Llama, Claude, Gemini, Qwen, Mistral, and BERT-family models.

• Advanced prompt engineering skills with demonstrated experience in implementing RAG patterns.

• High-level proficiency in Python and standard AI/ML libraries, such as LangChain, LlamaIndex, LangGraph, LangSmith, Hugging Face Transformers, Scikit-learn, and PyTorch/TensorFlow.

• Experience in implementing RAG architectures and prompt engineering.

• Strong background in fine-tuning, distillation techniques, and evaluation processes.

• Proficient in Python, SQL, Pandas, SciPy, Scikit-learn, ML model development, validation, deployment, and tuning.

• Experience in implementing anomaly detection.

• Familiarity with Snowflake Data Cloud and Snowflake Cortex AI.

• Extensive experience utilizing managed AI/ML services like Azure Machine Learning Studio and AI Foundry.

• Solid understanding of vector databases such as Weaviate and Neo4j.

• Knowledge of GenAI evaluation metrics including BLEU, ROUGE, perplexity, semantic similarity, and human evaluation.

• Capability to write high-quality, production-ready Python code with robust testing and maintainability practices.

• Proficient in deploying AI systems on Azure or AWS.

• Ability to develop and expose APIs using FastAPI and integrate with databases via an ORM.

• Competence in scaling GenAI solutions for enterprise-level workloads.

• Proven production experience with GenAI deployments on Azure or AWS.

• Strong track record of scaling AI solutions in live environments.

• Successfully delivered at least one production-level GenAI/Agentic AI solution.

• Familiarity with Model Context Protocol (MCP).

• Contributions to open-source GenAI initiatives.

• Excellent communication skills and the ability to work effectively with cross-functional teams.

• A bachelor's or master's degree in computer science, Information Technology, or a related discipline.

🏝️ Benefits

• Employees have the option to work remotely.