Vetted LangChain Professionals

Avni Tripathi

Screened ReferencesModerate rec.

Mid-level Data Scientist specializing in NLP, RAG, and information retrieval for RegTech

Gurgaon, India5y exp

“Built and deployed a production document Q&A/research platform that combines semantic search (vector DB embeddings) with structured knowledge-graph querying to reduce analyst research time. Used in high-stakes domains like Politically Exposed Person profiling and extracting critical information from ESG/regulatory documents, with a human-in-the-loop evaluation process (precision@k and source-text highlighting) to ensure accuracy.”

“Built and shipped a production LLM hallucination detection and monitoring pipeline using semantic-level entropy (embedding-clustered multi-generation variance) to flag unreliable outputs in downstream automation. Implemented a scalable async architecture (FastAPI + Docker + Redis/Celery) with strong observability (structured logs + PostgreSQL) and developed evaluation loops combining controlled prompts and human review; also partnered with non-technical stakeholders on AI-driven form validation/document processing.”

“Built and productionized a real-time social-media sentiment analysis system used by a marketing team to monitor brand/campaign performance. Experienced in orchestrating LLM workflows with LangChain (validation → prompting → parsing → post-processing), plus monitoring, retraining, and RAG-style retrieval using embeddings/vector stores to keep outputs reliable over time.”

“AI engineer who built an agentic, production-deployed LLM workflow for tobacco violation parsing and automated multi-case creation, using six specialized agents and a human-in-the-loop confidence-threshold routing design. Addressed data privacy constraints by generating synthetic datasets with LLM prompting, and orchestrated reproducible end-to-end pipelines in LangChain with robust testing and evaluation (precision/recall, micro-F1).”

“Backend/platform engineer who built an LLM-driven QA automation system (“mockmouse”) using a Flask orchestration microservice, Socket.IO real-time updates, Redis caching, and strict Pydantic schemas to turn prompts into reliable action graphs and automated browser tests. Has hands-on Kubernetes delivery experience (Docker/Helm/Jenkins) and has supported large migration programs, validating ETL cutovers with 1M+ synthetic records and rigorous output comparisons; also built event-driven monitoring/anomaly detection streaming into Grafana.”

“Backend/AI engineer with production experience in legal tech: built a high-scale licensing/subscription API (FastAPI/Postgres/Stripe) and shipped a RAG-based chatbot for an eDiscovery platform. Designed a robust legal document ingestion workflow that processes thousands of documents into a searchable vector index with clear retry/escalation logic, and has demonstrated measurable Postgres performance wins (200ms to 10ms) using EXPLAIN ANALYZE and composite indexing.”

Prasad Sadineni

Screened

Mid-level AI Engineer specializing in LLM fine-tuning, RAG, and agentic systems

Nashville, TN6y exp

“Building and deploying production in-house, domain-specific LLM chatbots for enterprises that cannot use third-party GPT tools due to internal policies. Focused on reducing latency and improving domain awareness using fine-tuning, continual learning, and advanced RAG/agent retrieval strategies, with experience orchestrating multi-agent workflows via LangChain/LlamaIndex and vector DBs (FAISS, Weaviate, Chroma).”

Shehab mohamed mohamed

Screened

Junior AI Engineer specializing in MLOps, LLMs, and multi-agent systems

Cairo, Egypt2y exp

“ML/AI engineer focused on production-grade systems, with experience building a low-latency multi-agent 'neural concierge' booking platform used across domains like restaurants and hospitals. Also worked on a healthcare computer vision system for nystagmus/eye-movement analysis, showing a mix of scalable LLM infrastructure, MLOps, and safety-conscious medical AI experience.”

Kevin Thomas

Screened

Intern Software Engineer specializing in AI, cloud, and backend systems

Torrance, CA1y exp

“Candidate has internship and graduate-project experience building AI agents, including a production log-analysis assistant using a lightweight agentic/RAG-style workflow with local GPT training and validation against historical logs. They also worked on Android/iOS game build and release processes in a Unity-based robot racing game environment, and highlight measurable LLM outcomes including 80% analysis accuracy, 2-5 second latency, and 50% cost reduction.”

sajda kabir

Screened

Junior Software Engineer specializing in AI, voice, and full-stack product engineering

Kolkata, India2y exp

“Product-minded full-stack engineer from SuperU who built AI voice-agent infrastructure end-to-end, from React/TypeScript campaign UIs to a forked n8n orchestration backend and Postgres multi-tenant data model. Stands out for shipping quickly in ambiguous startup environments, debugging deep reliability issues across layers, and delivering measurable gains like activation rising from 20% to 70%+ and call drops falling below 0.5%.”

“IBM Power/AIX engineer who has owned a large production estate (20+ Power9/Power10 frames and 400+ LPARs) with vHMC and dual-VIOS HA. Has hands-on incident recovery experience (NPIV/RMC issues, LPM restores) and PowerHA failovers, plus modern DevOps exposure using Terraform on AWS and CI/CD with GitHub Actions/Jenkins (including deploying AI/RAG and vision workloads).”

“Backend/AI engineer who built and refactored a production RAG system over IRS Form 990 filings for 60 nonprofits, using a dual-path architecture (deterministic financial ranking + TF-IDF semantic retrieval) to keep latency sub-2s and reduce hallucinations. Demonstrates strong API craftsmanship in FastAPI (contract-first, OpenAPI-driven) plus production-grade security for multi-tenant systems (JWT, RBAC, Supabase-style RLS) and careful migration practices (feature flags, traffic mirroring, incremental rollout).”

“Systems-focused C++ engineer who built a 32-bit CPU simulator end-to-end (custom ISA, full memory model, fetch-decode-execute loop) and solved tricky recursion/stack-frame correctness issues through heavy instrumentation and tracing. Has strong Linux and user-kernel boundary experience (procfs) plus modern build/test tooling (Docker, CI/CD, pytest), and is confident ramping quickly into ROS/ROS2 despite not having used it directly.”

“Built and productionized LLM-powered workflows that generate contextual insights from structured financial data, including prompt/retrieval design, data standardization, and reliability controls like rate limiting and batching. Also diagnosed and fixed real-time failures in an automated order validation system using logs/metrics, staging reproduction, edge-case handling, retries, and alerting, while supporting sales/customer teams with demos, scripts, and FAQs to drive adoption.”