No cost, no commitment - we'll make a personal intro
Priyanka Kaswan
Senior AI Research Engineer specializing in LLM agents and large-scale ML
AT&TPrinceton University7 Years ExperienceSenior LevelWorks On-Site
Connect with Priyanka
Priyanka already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Typically responds within 24 hours
Recommended
Already have an account?
About
AT&T Labs builder who deployed a production multi-agent LLM system that lets engineers ask natural-language questions and automatically generates deterministic, schema-grounded Snowflake SQL (200–400 lines) to detect anomalies in massive wireless/network event data (~11B events/day). Experienced with LangChain and Palantir Foundry orchestration, RAG-based result interpretation, and rigorous evaluation/monitoring loops to continuously improve reliability.
Hire with Reval
Find your next great hire
Our AI agents source, screen, and vet candidates for your open roles. Get qualified candidates within 48 hours.
LLM agent systemsSynthetic data generationLow-resource language NLPEdge/Distributed AI inferenceFederated learning5G/6G wireless MLModel monitoring and drift detection
Director of AI/ML Engineering specializing in MLOps, data platforms, and 3D computer vision
Teaneck, NJ10y exp
AetrexColumbia University
“Backend/data engineer focused on production ML/LLM systems: built a real-time FastAPI inference API on Kubernetes with strong reliability patterns (timeouts, idempotent retries, centralized error handling). Delivered AWS platforms using EKS + Lambda with GitHub Actions/Helm CI/CD and built Glue-based ETL from S3/Kafka into Snowflake with schema evolution and data-quality controls; also modernized legacy analytics/recommendation workflows into Python services with safe, feature-flagged cutovers.”
Junior Software Development Engineer specializing in cloud security and CI/CD
Herndon, VA2y exp
AmazonUniversity of Michigan
“Backend/security-focused engineer supporting a service with 100k+ monthly users. Built an automated load-testing suite that reproduced and mitigated catastrophic host failures from oversized SCP/rsync transfers via host-level throttling, and proposed a future sharding approach for very large transfers. Also created an internal agent to summarize anomalous metrics and provide ready-to-run debug queries, significantly reducing ops review time.”