Aaditey Pillai

About

Backend/ML engineer who built production LLM-enabled systems at PRGX, including an interpretable contract opportunity scoring engine (Bradley-Terry pairwise ranking) that reached 0.82 weighted Spearman agreement with SME auditors and was integrated into workflow. Also built a Duke student advisor chatbot and hardened it for real-world reliability/security with schema-driven tool calling, normalization, and off-domain defenses; led staged production rollouts with shadow testing and achieved 0.90 F1 on a new extraction field before shipping.

Experience

Education

Key Strengths

• Designed and shipped an LLM-assisted contract opportunity scoring engine integrated into auditor workflows
• Strong focus on interpretability in ML systems (Bradley-Terry pairwise ranking over deep models)
• Achieved 0.82 weighted Spearman correlation vs SME contract rankings
• API reliability patterns for LLM products (schema-enforced tool inputs, normalization, consistent response shapes, clarifying-question fallback)
• Led production pipeline migration with shadow-mode testing and staged rollout
• Delivered 0.90 F1 contract-number extraction before shipping to production
• Security-minded backend design (JWT auth, RBAC, tenant-scoped queries, abuse prevention, AI guardrails)
• Proactively identified conversational jailbreak/off-domain failure modes and hardened the system (re-grounding, confidence checks, tool restrictions)