Lead Software Engineer – GenAI, LLM, Python & Cloud AI

Your Team's Impact

FactSet's Funds Engineering team under DSE is focused on delivering Funds data (e.g., fund expense ratio, daily price & info data) coming from different sources by providing database solutions and automated processes which follow an Extract-Transform-Load (ETL) procedure. We develop & maintain an internal data collection application and manage funds data distribution services, routinely increasing efficiency year over year through automation.

Over time, the team has developed a robust and high-performing data pipeline capable of generating best in-class structured datasets that power FactSet’s products. Currently, the team is advancing this ecosystem by driving end-to-end automation across multiple stages of the pipeline. This includes the development of an event-driven, GenAI-centric, agent-based infrastructure aimed at enhancing efficiency, scalability, and innovation in data processing workflows.

What you’ll do

• Design, fine-tune, and deploy small and open-source large language models (LLMs) such as Llama, Mistral, OpenAI GPT, etc.
• Hands-on leadership in prompt engineering, few-shot prompting, and building advanced NLP/NLU workflows.
• Guide adoption of modern AI/ML frameworks (Hugging Face Transformers, LangChain, LangGraph, etc.) and architect reusable pipelines in Python.
• Drive critical systems architecture in Python, using best practices in API and microservices design (FastAPI, Flask, Django, etc.).
• Provide technical leadership to the development team, guide on architecture, design, and implementation decisions.
• Should lead and manage a technical team of 10 members.
• Provide technical support by incident resolution, and production troubleshooting
• Code quality through code reviews, advocating coding standards, and identifying risks before code reviews.
• Should collaborate with stakeholders and the healthy technical discussions engineering team.
• Supplements technical decision-making skills with broader business knowledge

What We’re Looking For

• 8-12 years of overall industry experience, including 3+ in senior or lead roles delivering ML/AI solutions in a cloud environment.
• Bachelor’s or master’s degree in computer science or equivalent
• Mastery of Python to build ETL pipelines, object-oriented patterns, code optimization, automated testing, and packaging.
• Experience with Database Relational database (MYSQL, POSTGRES, MSSQL or similar RDBMS)
• Experience on Cloud Technology AWS/Azure/GCP etc.
• Hands-on deployment and scaling of AI/ML services on AWS, Azure, or GCP; proficient in containers, serverless, and infrastructure as code.
• Effectively handle multiple projects, with different agendas and projects moving forward simultaneously
• Proven experience mentoring software engineers, shaping system design, and driving cross-team initiatives.
• Exceptional ability to explain complex technical subjects to diverse audiences.
• Excellent organization and time management skills (Time Management)
• Organized, self-directed, and resourceful with the ability to appropriately prioritize work in a fast-paced environment
• To effectively mentor others in the process for developing and ensuring high quality solutions
• Strong organizational and context switching ability

Desired Skills

• Experience in C++
• Experience with technologies like Pyspark , Databricks
• Experience with ML lifecycle tools, CI/CD pipelines, monitoring, and model governance.
• Secure cloud design, IAM, encryption, and compliance frameworks