Vetted Semantic Search Professionals

Srinivasan Gomadam Ramesh

Screened

Mid-level AI/Data Engineer specializing in agentic AI and data platforms

Redmond, WA7y exp

“AI/LLM engineer who built a production resume-parsing and candidate-matching platform at Quadrant Technologies, combining agentic LangChain workflows, VLM-based document template extraction (~85% accuracy), and a hybrid RAG backend for resume-to-JD search. Notably integrated automated LLM evals and metric-based CI/CD quality gates to catch silent prompt/model regressions, and led a 3-person team across frontend/backend/testing.”

“Built and shipped AI products at Humanitarians AI, including a full-stack multi-agent platform that consolidated six faculty AI tools into one interface and achieved 100+ user adoption, 70% less workflow switching, and a 6x latency improvement. Also designed a grounded document parser using FAISS and structured LLM outputs that reduced hallucinations by 60%, showing strong depth in both product-minded engineering and production AI systems.”

“Full-stack engineer with hands-on ownership of a production AI knowledge assistant used by 10,000+ daily users. Combines React/Next.js frontend work with FastAPI, AWS serverless, and RAG architecture using GPT-4, LangChain, and Pinecone, with measurable impact on relevance, latency, uptime, and support deflection.”

“Full-stack and AI systems engineer who has built across ride-hailing, fintech, higher-ed support, and legal-tech workflows. Stands out for shipping production RAG/agent systems with careful grounding and human fallback, while also delivering hard backend architecture wins like geospatial dispatch scaling and cutting fintech payment latency from 60 seconds to 2 seconds.”

“Backend/data engineer with hands-on production experience across Python/Flask microservices and AWS serverless/data platforms (Lambda, DynamoDB, S3, Glue/PySpark). Demonstrated strong reliability and operations mindset (JWT/RBAC, retries/timeouts/circuit breakers, CloudWatch/SNS alerting) and measurable performance wins (SQL report runtime cut from 10 minutes to 30 seconds). Seeking ~$150k base and cannot travel for onsite meetings for the next 5–6 months due to family medical constraints.”

“Full-stack/ML-leaning engineer who has shipped production-grade real-time analytics and an internal AI support assistant using RAG over enterprise documentation. Demonstrates strong systems thinking across scalability, reliability, observability, and LLM safety/evaluation (thresholded retrieval, RBAC, response validation, regression-gated evals), with concrete iteration based on performance metrics and user feedback.”

Shiva Dasi

Screened

Mid-level Software Engineer specializing in LLM agents and cloud-native systems

Boston, MA4y exp

“Built and shipped production LLM agents in compliance-sensitive environments (FERPA), emphasizing reliability via structured outputs, state-graph orchestration (LangGraph), and CI-driven eval/regression testing. Also has experience hardening messy ERP ingestion pipelines at scale (50K monthly orders) with normalization, idempotency/deduplication, and robust failure handling using AWS (SQS/CloudWatch) and PostgreSQL.”

Jyothsna V

Screened

Mid-level Backend Software Engineer specializing in Python/FastAPI and cloud-native microservices

USA4y exp

“Backend engineer who evolved Coca-Cola bottlers' Trade Promotion Optimization platform at Coke One North America, building domain-focused microservices in Node.js and Python (Flask/FastAPI) with PostgreSQL. Experienced in multi-tenant security (OAuth2/JWT, RBAC, row-level scoping by bottler/region), API contract/versioning discipline, and Azure DevOps-driven incremental rollouts with strong observability.”

Nagendra Reddy Palugulla

Screened

Mid-level Machine Learning Engineer specializing in LLMs, RAG, and MLOps

Florida, United States4y exp

“Built and shipped a production real-time content moderation platform for Zoom/WebEx-style meetings, combining Whisper speech-to-text with fast NLP classifiers and REST APIs to flag hate speech, bias, and HIPAA-related content under strict latency constraints. Demonstrates strong MLOps/infra depth (Airflow, Kubernetes, Terraform/Helm, observability) and a pragmatic approach to reducing false positives via threshold tuning, context validation, and hard-negative data—while partnering closely with compliance and product stakeholders.”

Keeravani Chekuri

Screened

Mid-level AI/ML Engineer specializing in LLM systems and MLOps

Boston, MA3y exp

“Built and deployed an AI tutoring assistant end-to-end at Nexora School, spanning discovery with school districts, multi-agent LangGraph/RAG architecture, AWS Bedrock migration, and post-launch stabilization. Stands out for combining hands-on LLM systems engineering with strong educator-facing trust building, FERPA-driven architecture decisions, and disciplined production practices around evals, logging, and messy document ingestion.”

“Built and deployed a full-stack web product for international football fans visiting the U.S. for FIFA, owning everything from crawling and aggregating event data to frontend, backend, deployment, and maintenance. Particularly strong in data-heavy product work, using LLMs, Google Maps API, and SQL/RPC patterns to improve data quality, speed implementation, and support a polished user experience.”

“AI-focused software engineer who has built production CRM intelligence features including audio transcription, summarization, and action-item extraction, plus a multi-agent LLM/NLU pipeline using Supabase, Node.js, RabbitMQ, and CloudWatch. Stands out for a disciplined approach to AI-assisted coding: treating AI like a junior developer, rigorously testing outputs, and refining prompts to prevent hallucinations in real business workflows like resume screening.”

Shalini Jada

Screened

Mid-level Full-Stack Engineer specializing in Applied AI

Bridgeport, CT4y exp

“Full-stack AI engineer focused on operational and healthcare analytics use cases, with hands-on experience building React/TypeScript frontends and Node/FastAPI/Flask backends for agentic systems. Stands out for combining LLM orchestration, retrieval grounding, and human-in-the-loop controls with measurable business impact, including a fraud detection dashboard that achieved 92% accuracy and cut manual review time by 85%.”

“At ReferU.AI, designed and deployed an agentic RAG pipeline that automates multi-jurisdiction legal document drafting, emphasizing hallucination reduction through hybrid retrieval, validation agents, guardrails, and iterative regeneration. Experienced with orchestration frameworks (especially CrewAI) and rigorous testing/evaluation practices including human-in-the-loop review, adversarial testing, and production metrics/logging.”

“Full-stack engineer with very strong TypeScript/React frontend depth and Python backend ownership across Django, FastAPI, and distributed systems. Built and operated production platforms on AWS/Kubernetes, including a distributed code execution system with PostgreSQL/Redis reliability patterns and an LLM-based intent classification layer that they debugged and hardened in production. Particularly compelling for teams needing someone who can improve performance, reliability, and architecture in fast-moving product environments.”

“Built and deployed production NLP/LLM systems including a multilingual (5-language) health misinformation detection pipeline with latency optimization (batching/quantization/caching) and explainability (gradient-based attention visualizations). Experienced orchestrating end-to-end AI workflows with Airflow and Prefect, and partnering with customer support ops to deliver an AI agent for ticket summarization and priority classification with clear, measurable acceptance criteria.”

“Built and deployed an LLM-to-SQL automation system in a closed/internal environment, using a retriever–reranker–validator architecture on Kubernetes with strong security controls (semantic + rule-based validation and RBAC), achieving 99% uptime and cutting manual query time ~40%. Also worked on genomic sequence classification and semantic search workflows, orchestrating data prep with Airflow, tracking/deploying with MLflow, and optimizing distributed multi-GPU training on a university Kubernetes cluster.”

“At Provenbase, built and shipped a production LLM-powered semantic search and candidate matching platform (RAG with GPT-4/Gemini, multi-agent orchestration, Elasticsearch vector search) to scale sourcing across 10M+ candidate records and 1000+ data sources. Drove sub-second performance, cut LLM spend 30% with routing/caching, and improved recruiting outcomes (+45% sourcing accuracy; +38% visibility of underrepresented talent) through bias-aware ranking and tight collaboration with recruiting stakeholders.”

Hemanth Suddala

Screened

Mid-level GenAI Engineer specializing in LLM automation, RAG, and document intelligence

Boca Raton, FL3y exp

“Built and deployed a production GenAI resume screening and matching system for Florida Atlantic University, focused on improving recruiter efficiency and search relevance. Demonstrates strong RAG engineering (embeddings, query rewriting, metadata filtering, threshold tuning) plus practical reliability work (grounding constraints, fallbacks, and evaluation using real user queries) using Python REST APIs and orchestration frameworks like LangChain and LlamaIndex.”

Arunim Samudra

Screened

Mid-Level Software Engineer specializing in LLM applications, RAG, and OCR automation

Austin, TX3y exp

“At Trellis, built and shipped a production multi-agent, authenticated GenAI chatbot for sensitive financial account inquiries (loan/payment lookups), using dynamic model routing to control latency and cost while improving accuracy. Implemented prompt-injection defenses (Meta Prompt Guard), RAG with LangChain, and LLM-as-a-judge evaluation; the system cut manual support call volume by 40%+ and was refined through close collaboration with QA-driven user testing.”

Anita Bhagashetti

Screened

Mid-Level Software Engineer specializing in distributed systems and cloud microservices

3y exp

“Built and productionized a RAG-based semantic search system for video-derived data, focusing on measurable success metrics (p95 latency, reliability, cost/request) and strong observability (prompt versions, retrieved docs, tool calls, token usage). Experienced in diagnosing real-time issues in LLM/agentic workflows and in supporting go-to-market efforts through tailored technical demos, rapid POCs, and post-close onboarding.”

“Bootstrapped founder of FAMRO LLC with 15+ years spanning startups and corporate roles, including COO experience at an AI/ML startup that built a retail marketing analytics product using camera feeds. Also worked on a clean-tech venture, EnerIO, which won 1st position from Pakistan and was invited to pitch at the GCIP/GEF event in San Francisco in 2015.”

Rohit Viswakarma Pidishetti

Screened

Mid-level Full-Stack Engineer specializing in real-time frontend systems

New York City Metropolitan Area, USA5y exp

“Frontend-leaning full-stack engineer who built and largely owned YAARI, a browser-based social media platform with real-time interactions, media handling, and AI-based content validation. Stands out for combining React performance tuning, real-time UX design, and security-conscious backend integration in a complex consumer-style application.”

“Full-stack/backend engineer with recent hands-on depth in Go, Python, React, and TypeScript, spanning telehealth, banking, and B2B workflow platforms. Particularly compelling for startup and scale-up environments: rebuilt core telehealth services to restore provider trust and support 150% user growth without adding servers, and has also delivered large-scale banking and compliance-sensitive systems in production.”