Overview

Position: NLP Engineer
Company: TIFIN RM
Duration: January 2025 - Present
Location: Remote

Upon graduating and joining TIFIN RM full-time as an NLP Engineer, I transitioned from primarily research-focused work to owning end-to-end delivery of production NLP features. This role has deepened my appreciation for the full lifecycle of deploying machine learning systems in enterprise environments.

Key Achievements

Production System Optimization

  • Led production deployment of semantic caching system, successfully migrating to MPNet embeddings
  • Achieved sustained latency improvement of over 2.5 seconds—a more than 40% reduction that dramatically enhanced user experience for financial advisors
  • Expanded system coverage by developing automated query variation generators and implementing sophisticated deduplication methods

Alternative Investments Expansion

  • Spearheaded expansion of TIFIN RM’s capabilities to support alternative investments—hedge funds, private equity, and other non-traditional assets
  • Developed sophisticated intent recognition to distinguish between traditional and alternative investment queries
  • Expanded entity recognition systems to handle new product categories while ensuring consistent performance across the expanded domain

Production Excellence

  • Resolved critical production issues affecting customer demonstrations
  • Optimized response generators through aggressive prompt engineering
  • Systematically improved data quality through anonymization and misclassification correction
  • Managed the inherent tension in production ML systems: maintaining stability for existing users while continuously improving capabilities

Technical Skills Developed

  • Production ML Systems: End-to-end deployment and maintenance of machine learning systems at enterprise scale
  • Financial Domain Expertise: Deep understanding of traditional and alternative investment products
  • System Optimization: Balancing performance, reliability, and feature expansion in production environments
  • Collaborative Engineering: Working with cross-functional teams to deliver customer-facing features

Impact

This experience has demonstrated that my research capabilities translate effectively to production environments and has reinforced my desire to pursue graduate studies where I can develop deeper theoretical foundations while continuing to focus on AI systems with real-world impact.

The role has taught me that impactful AI engineering requires not just technical sophistication but also collaboration, systematic debugging skills, and a deep understanding of user needs in high-stakes financial environments.