Vetted GPT-4 Professionals

“AI/ML Engineer (TCS) who built and deployed a production LLM-powered audit transaction validation service to reduce manual review of unstructured transaction records and comments. Implemented a LangChain/Python pipeline for extraction/normalization and discrepancy detection, with strong production reliability practices (decision logging, dashboards, labeled eval sets) and a human-in-the-loop auditor feedback loop to improve precision/recall under strict data-sensitivity and near-real-time constraints.”

“Built and deployed a GPT-4-powered medical assistant for clinical staff to reduce time spent searching guidelines and EHR information, with a strong emphasis on safety and compliance. Uses strict RAG, confidence thresholds, and fallback behaviors to prevent hallucinations, and runs production-grade workflows orchestrated with LangChain/LangGraph plus Docker/Kubernetes/MLflow and monitoring for reliability and cost.”

“LLM/ML engineer who has shipped an enterprise RAG-based Q&A system (LangChain/LlamaIndex, FAISS + Azure Cognitive Search, GPT-3.5/4 via OpenAI/Azure OpenAI) to production on Docker + Kubernetes/OpenShift, tackling hallucinations, retrieval quality, latency/cost, and RBAC/IAM security. Also partnered with operations leaders to turn manual reporting into an LLM-powered summarization and forecasting dashboard driven by real KPIs and iterative stakeholder feedback.”

“Built a production RAG-based “unified assistant” that consolidates siloed company documents into a single chatbot while enforcing fine-grained access control via RBAC/metadata filtering with OAuth2/JWT. Experienced orchestrating LLM workflows with LangChain/LangGraph + FastAPI (async + caching) and measuring performance via retrieval accuracy and response-time SLAs. Also delivered a churn analytics solution with dashboards and automated retention campaigns using n8n.”

“Built and deployed a production RAG-based document Q&A system on Azure OpenAI to help business teams search thousands of PDFs/Word files, using Qdrant vector search, MongoDB, and a Flask API. Demonstrates strong production engineering (streaming large-file ingestion, parallel preprocessing, monitoring/retries) plus systematic prompt/embedding/chunking experimentation to improve accuracy and reduce hallucinations, and has hands-on orchestration experience with ADF/Airflow/Databricks/Synapse.”

“Currently at Huntington Bank, built a production-grade RAG system that helps business/operations teams get grounded answers from large volumes of internal enterprise documents. Owns ingestion and FastAPI backend, tuned hybrid BM25+vector retrieval and chunking for relevance, and evaluates reliability with metrics and observability (LangSmith, CloudWatch, Prometheus/Grafana) while partnering closely with non-technical stakeholders.”

Kasireddy Kumar reddy

Screened

Mid-level AI/ML Engineer specializing in healthcare, fraud detection, and recommender systems

Missouri, USA6y exp

“Healthcare-focused applied ML/LLM engineer who has deployed production systems including an LLM medical documentation assistant that summarizes unstructured EHR notes into physician-ready structured outputs. Experienced building secure, compliant pipelines (PHI minimization, RBAC, encryption) and scaling via Docker/Kubernetes/Azure ML, plus orchestrating ETL/ML workflows with Airflow and Kubeflow; also built an LLM-driven clinical coding assistant at Centene with measurable performance metrics.”

“Built and shipped LLM-powered agents including a production RAG research assistant that cut research lookup time from ~20 minutes to ~10–20 seconds using caching, retrieval thresholds, and citation-enforced grounded answers. Also designed multi-step, tool-calling workflows with stateful critique/revision loops and pragmatic monitoring (retry/schema-failure/low-confidence signals) plus normalization/validation layers for messy notes/spreadsheet-style data.”

Pavan Punna

Screened

Mid-level AI/ML Engineer specializing in LLMs, MLOps, and healthcare-fintech AI

Dallas, TX5y exp

“Built and owned a production GPT-4 RAG assistant for clinical and enterprise query resolution, taking it from initial experiment to deployment, monitoring, and iterative improvement. Their work cut resolution time from 45 minutes to under 2 minutes, achieved roughly 95% accuracy, and scaled to thousands of additional monthly queries while emphasizing safety and trust in a sensitive clinical domain.”

“ML/AI engineer at PNC who has shipped enterprise-grade RAG and document intelligence systems for compliance and policy workflows. Stands out for combining LLM product thinking with production rigor—owning FastAPI/Kubernetes deployments, monitoring, evaluation, and human-feedback loops that drove measurable gains like 40% faster policy search and 30% faster compliance review.”

ASHISH DONDAPATI

Screened

Mid-level AI/ML Engineer specializing in Generative AI for Financial Services

San Francisco, USA6y exp

“ML/AI engineer with strong financial-services domain experience who has built production systems spanning trade anomaly detection, investment-research RAG, and agentic LLM workflows. Particularly compelling for teams needing someone who can take ML/GenAI from prototype to monitored production while balancing compliance, latency, cost, and reliability.”

Siva Harini Sri Janaki Raman

Screened

Mid-level Data Engineer specializing in cloud data platforms

Dallas, TX3y exp

“Built an AI-powered internal support assistant at CVS Health using GPT-4, LangChain, and Pinecone, applying RAG, validation, and monitoring to reduce repetitive support tickets while protecting sensitive healthcare data. Stands out for a pragmatic approach to AI engineering: using multi-agent and LLM workflows to accelerate development while keeping systems constrained, observable, and production-friendly.”

“Built and shipped a production LLM-powered internal operations automation platform using LangChain RAG (Pinecone) and FastAPI microservices, deployed on AWS EKS, serving 10k+ daily interactions. Implemented a rigorous evaluation/observability stack (golden datasets, prompt regression tests, MLflow, retrieval metrics, hallucination monitoring) that drove hallucinations below 2% and improved reliability, and partnered closely with non-technical ops leaders to cut manual lookup work by 60%+.”

“Distributed-systems engineer applying robotics-style patterns to software: built "Vibecheck," a high-throughput real-time video + OS-telemetry fusion and analysis system (500+ MB/session) with strict latency constraints. Strong in containerization and CI/CD (Docker, GitHub Actions) and in designing fault-tolerant, event-driven architectures (Kafka/RabbitMQ), plus hands-on debugging of multi-agent coordination using blackboard + watchdog/circuit-breaker control patterns.”

Uday kumar swamy

Screened

Senior Machine Learning Engineer specializing in MLOps and NLP/GenAI

Chicago, USA9y exp

“Built a production LLM-agent framework for a startup that performs daily financial/trading analysis by combining live market data with internal tools, including a centralized memory module to prevent context drift and reduce hallucinations. Also implemented an Airflow-orchestrated retail price forecasting pipeline deployed to AWS endpoints, scaling parallel workloads via Kubernetes Executor and validating systems with rigorous functional + LLM-specific metrics and cross-team collaboration.”

“Built an LLM-powered customer segmentation agent during a Chewy internship, consolidating Snowflake data into a knowledge graph so non-technical marketing users could query customer cohorts in natural language. Stands out for combining agent/tooling design with rigorous data engineering practices, including schema audits, imputation, validation layers, and idempotent pipelines on messy large-scale datasets.”

“At HPE, led and deployed an enterprise-grade LLM document intelligence platform for an insurance client, automating extraction from highly variable PDFs/scans/emails and raising field accuracy from 74% to 93%. Built a LangChain/Pinecone/OpenSearch RAG framework to cut hallucinations by 37% and operationalized LangSmith evals in CI, driving a 41% triage accuracy lift and >33% fewer incorrect resolutions while partnering closely with claims operations via HITL workflows.”