Vetted Semantic Search Professionals

“Candidate has built multiple zero-to-one AI/full-stack products spanning bioinformatics search, rental marketplace semantic search, and an SDR agent for a hospitality startup. Particularly strong at turning LLM/embedding concepts into usable products with modular workflows, explainable outputs, and production-minded infrastructure.”

Abhinita Sanabada

Screened

Senior Software Engineer specializing in AI/ML systems and FinTech platforms

San Jose, CA9y exp

“Master’s student in Data Science at San Jose State University with prior software engineering experience at JPMorgan Chase and Zap Labs. She combines enterprise backend reliability work in financial systems with hands-on full-stack AI workflow projects, including a recruiting automation system built with React/Next.js, FastAPI/Node, Kafka, and WebSockets, with a strong emphasis on observability, human-in-the-loop controls, and maintainability.”

“Frontend-focused engineer with experience spanning healthcare, enterprise analytics, and real-time trading products. They have owned React/TypeScript dashboard surfaces end-to-end, including a hospital patient dashboard that cut latency by 50%, and have also shaped backend WebSocket contracts to make real-time systems scale.”

“Full-stack engineer with hands-on ownership of an internal LLM platform, spanning React/NestJS development, PostgreSQL schema design, multi-provider model integrations, and chat/eval pipelines. They also show strong production engineering instincts, having resolved Cognito throttling failures via tracing and led an observability migration to Signoz that materially improved incident diagnosis speed.”

Prashant Singh

Screened

Mid-level Backend/Platform Engineer specializing in data pipelines, reliability, and AI-assisted ingestion

8y exp

“Backend engineer who built and scaled a blockchain-based e-voting platform at early-stage startup Elemential Labs, balancing decentralization with real-world operability by centralizing control-plane components while keeping the ledger immutable. Has hands-on experience migrating high-throughput ingestion from Kafka to AWS Kinesis with parallel cutover, strengthening data integrity and read-after-write consistency (Elasticsearch), and hardening pipelines against silent data-quality failures via anomaly detection and self-healing automation.”

Harshal Sawant

Screened

Senior AI Engineer specializing in LLMs, RAG, and MLOps on multi-cloud

8y exp

“Built and productionized a secure internal RAG-based AI assistant (LangChain/FastAPI/FAISS on GCP), tackling real-world issues like latency, retrieval speed, and hallucinations—delivering 25% faster retrieval and 99.9% uptime. Also implemented scalable, reliable ML retraining orchestration with AWS Step Functions/SageMaker/Lambda and partners closely with compliance analysts to iteratively refine prompts and outputs to meet governance standards.”

“Built and owned end-to-end production Conversational AI and RAG systems at Nike for customer support and product search, with strong evidence of measurable impact. Combines LLM product thinking with solid platform engineering, including evaluation pipelines, monitoring, safety controls, and reusable FastAPI frameworks that improved both user outcomes and team velocity.”