Vetted Semantic Search Professionals

“Built and deployed a production LLM-based RAG agent platform adopted by multiple business teams (Marketing, GTM, Recruiting, Customer Support) to automate knowledge search, Q&A, and content generation. Emphasizes production-grade reliability (grounding/validation/guardrails), rigorous evaluation/monitoring, and cost-aware scaling via model tiering, prompt/retrieval optimization, and caching using LangChain/LangGraph orchestration.”

“ML/NLP practitioner who built a retrieval-augmented generation (RAG) system for large financial and operational document sets using Sentence-Transformers (all-mpnet-base-v2) and a vector DB (e.g., Pinecone), with a strong focus on retrieval evaluation and chunking strategy optimization. Experienced in entity resolution (rules + embedding similarity with type-specific thresholds) and in productionizing scalable Python data workflows using Airflow/Dagster and Spark.”

“Recent J&J intern who built a conversational RAG agent and led a shift from a monolithic model to a modular RAG workflow, cutting response time from several days to under a second by tackling data fragmentation, context retention, and embedding/latency optimization. Also worked on a large (7B-parameter) multimodal VQA pipeline for healthcare research and stays current via NeurIPS/ICLR and open-source contributions.”

“Built a secure, on-prem/private GPT assistant to replace manual SharePoint-style search across thousands of policies/SOPs/engineering docs, using a production RAG stack (LangChain/LangGraph, FAISS/Chroma, PyMuPDF+OCR, vLLM). Implemented layout-aware ingestion (including table-to-JSON) and a multi-agent retrieval/generation/verification workflow with strong observability and compliance guardrails, delivering ~70% reduction in search time.”

“ML/AI practitioner with hands-on experience deploying models to production and optimizing for low-latency inference using pruning/quantization, with deployments on AWS SageMaker and Azure ML. Has orchestrated end-to-end ML pipelines with Airflow and Kubeflow (ingestion through evaluation) and emphasizes reproducibility via containerization and version-controlled artifacts, while effectively partnering with non-technical stakeholders using dashboards and business-aligned metrics.”

“Data/ML practitioner with experience at Airtel and Lincoln Financial delivering measurable business outcomes: improved retention 15% via NLP sentiment analysis and cut response time ~25% using sentence-BERT + FAISS semantic linking. Strong in data quality/identity resolution (SQL + fuzzy matching) and in building production-grade Python workflows orchestrated with Airflow/AWS Glue, including validation and dashboard integration in Power BI.”

Chandan Chalumuri

Screened

Mid-level Data Scientist specializing in ML, NLP, and Generative AI

Tempe, AZ4y exp

“Data engineering / ML practitioner with experience at MetLife building transformer-based sentiment analysis over large unstructured datasets and productionizing pipelines with Airflow/PySpark/Hadoop (reported 52% efficiency gain). Also implemented embedding-based semantic search using Pinecone/Weaviate to improve retrieval relevance and enable RAG for customer support and document matching use cases.”

Sharanya Rao

Screened

Mid-level AI/ML Engineer specializing in NLP, LLMs, and RAG for finance and healthcare

Remote, USA3y exp

“Built an AI lending assistant (RAG + DeBERTa) used by credit analysts to retrieve policies and past loan decisions, tackling real production issues like hallucinations, document quality, and sub-second latency. Deployed a modular, Dockerized AWS architecture (ECS/EMR + load balancer) with load testing, caching/precomputed embeddings, and CloudWatch monitoring, and used Airflow to automate scheduled data/embedding/vector DB refresh pipelines with retries and alerts.”

Madhu Sriram Sengottu Velan

Screened

Entry-Level Software Engineer specializing in backend systems and distributed services

Chennai, IN2y exp

“Backend/AI engineer from an early-stage Japan-based startup (WorkAI) who built a multi-tenant RAG system integrating Notion/Slack/Google Drive with Pinecone and OpenAI, including a chatbot retrieval workflow. Experienced in production reliability (rate limits, retries, verification layers), strong Python/FastAPI engineering practices, and PostgreSQL performance optimization; currently based in India and needs sponsorship.”

Phani K

Screened

Mid-level AI/ML Engineer specializing in GenAI, NLP, and healthcare-financial ML

Terre Haute, IN4y exp

“ML/AI engineer with hands-on experience shipping healthcare AI systems, including an oncology risk prediction platform and RAG-based clinical decision support tools. Stands out for combining clinical domain context with strong production engineering across Spark, FastAPI, AWS SageMaker, monitoring, evaluation, and safety guardrails.”

“GenAI engineer who has deployed production LLM/RAG chatbots for internal document search, focusing on reliability (hallucination reduction via prompt guardrails + retrieval filtering) and performance (latency improvements via caching). Experienced with LangChain/LangGraph orchestration for multi-step agent workflows and iterates using monitoring/logs and benchmark-driven evaluation while partnering closely with product and business teams.”

“Backend-leaning full-stack engineer who ships AI-enabled products end-to-end: built CodeChat, a production internal codebase Q&A tool using RAG with Pinecone and a model-agnostic wrapper across OpenAI/Anthropic/AWS Bedrock, cutting AWS costs ~50% and latency ~45%. Also built and operated RealityStream, a Flask-based real-time forecasting API with JWT/RBAC, MLflow model versioning, and Prometheus/Grafana observability, including handling a real production latency incident via rollback, preloading, and caching.”

“Built and shipped production RAG-based LLM agents automating multi-step document query workflows, emphasizing reliability via monitoring, retries, structured exception handling, and fallback retrieval (alternative embeddings/keyword search). Demonstrated measurable gains (18% latency improvement, 25% retrieval efficiency, 12% precision) and has experience integrating agents with messy tax and transaction data at RSM using validation/cleaning and idempotent design.”