Vetted Semantic Search Professionals

“Early-career/new-grad candidate who built TrendScout AI, an evidence-first market intelligence agent that ingests messy news, extracts entities/events, builds a Neo4j knowledge graph, and answers questions via RAG with citations. Achieved ~95% retrieval relevance by combining ChromaDB semantic search with graph-based retrieval and validating outputs through human evaluation and guardrails to prevent hallucinations.”

“Built production AI systems for Macy's and Bloomingdale's, including an embeddings-based pipeline to clean trending search queries and an end-to-end 'Ask Macy's' multi-agent chat experience. Brings hands-on experience with real-world agent orchestration, tool integration, quality evaluation, and business-facing safeguards in a large-scale e-commerce environment.”

Aniket Dhanawade

Screened

Mid-level Full-Stack Engineer specializing in cloud-native and AI-powered applications

USA3y exp

“Candidate has a thoughtful, hands-on approach to AI-assisted software development, treating AI as a pair programmer while retaining ownership of architecture, tradeoffs, and final code quality. They have practical experience using multi-agent workflows to ship small features end-to-end, including planning, execution, and gap detection under human oversight.”

“LLM/agentic systems engineer who built a production "Agentic AI Diagnostic Assistant" for network engineers, using a multi-agent Llama 2 + LangChain architecture with RAG over telemetry/incident data in DynamoDB and confidence-based deferrals to reduce hallucinations. Also has strong MLOps/orchestration experience (Airflow, EventBridge, Spark, Docker, SageMaker/ECS) at multi-terabyte/day scale and delivered multilingual NLP analytics (fine-tuned BERT/spaCy) for support operations through hands-on stakeholder workshops.”

“Built production LLM/RAG platforms for financial services to enable natural-language Q&A over large policy/compliance document sets stored in Snowflake and SharePoint. Strong in MLOps and orchestration (Airflow, ADF, Step Functions, MLflow) and in solving real production issues like stale embeddings and model performance, including an incremental Snowflake Streams sync that cut processing time from hours to minutes.”

“ML/AI engineer with defense and commercial analytics experience: deployed a real-time aerial object detection system at Dynetics (YOLOv5 + TorchServe in Docker on AWS EC2) with drift-triggered retraining and 99.5% uptime, tackling ambiguous targets and weather degradation. Previously at Fractal Analytics, built and explained a churn prediction model for marketing stakeholders using SHAP and delivered it via a Flask API into dashboards, driving a reported 22% attrition reduction.”

“ML/NLP practitioner with banking experience (M&T Bank) who has built a GPT-4 RAG system using LangChain and Pinecone to connect unstructured customer data with internal knowledge bases, improving accuracy and reducing manual lookup time by 50%+. Strong in entity resolution and productionizing scalable Python data workflows, including major performance wins by migrating bottleneck joins from Pandas to Dask.”

“Built and productionized an LLM-powered support/knowledge pipeline using embeddings and retrieval (RAG) to deliver more grounded, higher-quality responses while reducing manual effort. Focused on real-world reliability and performance—adding structured validation/guardrails, optimizing vector search and context size for latency/scale, and monitoring failure patterns in production. Experienced with orchestration via LangChain for LLM workflows and Airflow for production data/ML pipelines, and iterates closely with operations stakeholders through demos and feedback.”

“Backend engineer who built an AI-driven "Smart Feedback Analyzer" API (Flask → FastAPI) that processes user feedback with NLP (Hugging Face + OpenAI) and returns structured insights. Demonstrates strong production-minded architecture: stateless services, Cloud Run + Docker deployment, Redis/Celery background processing, and Postgres/SQLAlchemy performance tuning (EXPLAIN ANALYZE, indexing, N+1 fixes), plus multi-tenant data isolation via JWT/API-key derived tenant IDs.”

“Founding engineer at Novum AI building a real-time call analytics/suggestion backend (transcription + sentiment/tone + context retrieval) using a serverless architecture. Drove major latency improvements (about 4s down to sub-1.5s) and has practical experience hardening production APIs (FastAPI/Pydantic, auth with Cognito/Redis) and payment systems (Stripe) by surfacing overlooked subscription and multi-tenant billing edge cases.”

“Built and productionized an LLM/RAG-based credit case triage system that indexes credit bureau narratives and delivers structured, source-linked summaries for analysts. Emphasizes production reliability (data masking, human-in-the-loop review, abstention/fallbacks, monitoring) and reports >99% uptime plus ~30% efficiency gains, with iterative improvements driven by offline/online evaluation and schema-aware validation.”

Sumasri Jasti

Screened

Mid-level GenAI Engineer specializing in LLM agents and RAG systems

USA3y exp

“Designed and deployed a production LLM agent platform at the National Institutes of Health to reduce time spent searching fragmented internal documentation, combining RAG grounding with multi-step tool-calling workflows and integration into legacy services via inference APIs. Emphasizes production-grade reliability through automated evaluation on real queries, guardrails/safe-failure behaviors, and ongoing A/B testing and monitoring, and has experience translating non-technical stakeholder goals into measurable success metrics.”

“Analytics professional with Intuit experience spanning modern data stack work, behavioral segmentation, and applied AI. They built dbt/Snowflake pipelines powering retention and churn dashboards, automated feedback classification with OpenAI/LangChain, and partnered closely with product and marketing teams to turn analytics into onboarding, targeting, and lifecycle messaging decisions.”

“ML/AI engineer with hands-on experience building production MLOps systems for predictive maintenance and demand forecasting, including deployment, monitoring, and iterative retraining. Also shipped a RAG-based employee onboarding chatbot integrated with ServiceNow APIs and reports business impact of roughly $300k/month in reduced stockout and overstock costs.”

“Built from scratch a social media analytics MVP featuring an LLM-powered semantic search agent that became a core part of the product experience within a 6-week deadline. Stands out for focusing on production readiness early—retrieval-first design, explicit tool constraints, structured outputs, idempotent services, and practical eval/monitoring loops rather than demo-only AI.”

“Built a production-grade LLM document processing and workflow orchestration platform at CBRE for internal operations teams, handling highly variable long-form documents with a reusable architecture involving 50+ coordinated LLM calls per request. Stands out for treating agentic systems like distributed backend infrastructure, with strong emphasis on evaluation, observability, reliability, and vendor-agnostic orchestration across Bedrock, Vertex AI, and OpenAI.”