Vetted LangChain Professionals

“At PwC, built and productionized an agentic RAG enterprise search assistant over 6M internal documents (8M embeddings), deployed across AWS and GCP. Drove major retrieval gains (72%→92% precision via BM25+dense hybrid with RRF and cross-encoder re-ranking), reduced hallucinations 30%, achieved <2s latency at 50–60K queries/month, and cut support tickets 30%—boosting adoption to 2,500 users by adding source-cited answers.”

Sreenaina Koujala

Screened ReferencesStrong rec.

Mid-level Full-Stack & AI Engineer specializing in cloud and intelligent systems

Ashburn, VA8y exp

“Builder with experience across government contracting, engineering automation, and solo AI product development. They architected a serverless AWS pipeline that converted unstructured BIM data into IFC 3D models, built an enterprise internal-data chatbot with auditability and guardrails at Steampunk, and independently launched an AI study platform using Claude. Strong fit for early-stage or ambiguous environments where end-to-end ownership and practical AI systems matter.”

“Worked on onboarding a Middle East logistics client processing thousands of invoices/month, building a production-ready pipeline that routes known vendor PDFs to deterministic regex parsers via Tax ID matching and falls back to LlamaParse for unknown layouts. Added financial consistency validation plus human-in-the-loop review and logging/metrics to continuously reduce LLM usage and improve template coverage.”

Daniel Jeong

Screened

Junior Full-Stack Engineer specializing in real-time platforms and AI tools

Cambridge, MA3y exp

“Early-career full-stack engineer with unusual depth in mission-critical environments: helped build a cybersecurity operations platform from scratch as the third engineer and shipped it to the National Election Commission of South Korea. Also worked on defense-focused situational awareness software, combining React/WebGL frontend performance work with backend data transformation for real-time weather and map overlays.”

“Full-stack developer with capstone and project experience delivering production-ready systems in unstructured environments, including a Faculty Tracking system for real departmental use. Strong in React performance debugging (re-render optimization with useMemo), Prisma-backed multi-database setups (MySQL local / SQL Server production on a UCI Health VM), and end-user support workflows that feed back into improved Help documentation.”

Praneeth Regonda

Screened

Mid-level Full-Stack Engineer specializing in FinTech and AI platforms

New York, NY4y exp

“Full-stack engineer with 3 years of AI/ML experience who has shipped production LLM workflows, including a Bloomberg triage dashboard that cut manual processing by 35%. Combines React/TypeScript product sense with AWS/Spring/Lambda backend architecture and unusually strong practical judgment around evals, trust, retrieval, latency, and UX for real-world AI systems.”

“Solutions architect/technical consultant with experience across Intuit, Deloitte, and CodeNest Solutions, focused on enterprise data modernization, AI adoption, and real-time streaming in B2B environments. Particularly strong in regulated financial use cases, where they combine hands-on POC building, security/compliance diligence, and modern data stack expertise to help clients modernize legacy systems and close complex enterprise deals.”

“Robotics ML/software engineer focused on Vision-Language-Action control for 7-DoF robots, replacing tokenized action decoding with continuous regression heads (including a logit-weighted expectation approach) to improve stability and real-time behavior. Strong in ROS1/ROS2 systems integration and debugging closed-loop manipulation issues via latency instrumentation, QoS-aware distributed messaging, and sim-to-real validation using Gazebo/Unity, Docker, and CI pipelines.”

“At Esri, the candidate is building a production LLM-powered WebGIS AI framework that embeds an AI assistant into web maps and routes natural-language requests into ArcGIS JavaScript SDK functions via a LangGraph-orchestrated, multi-agent system. They emphasize production reliability and scale (strict tool calling/JSON, live schema validation, query guardrails) and rigorous evaluation/observability using LangSmith, offline prompt datasets, and latency/tool-call accuracy tracking.”

“Built and deployed a production RAG-based LLM Q&A and summarization platform for internal documents, emphasizing grounded answers with structured prompting and citations to reduce hallucinations. Experienced orchestrating end-to-end LLM workflows with LangChain plus cloud pipelines (Azure ML Pipelines, AWS), and runs iterative evaluation using both metrics (accuracy/hallucination/latency/cost) and real user feedback to drive reliability.”

“Built a production-grade agentic document intake system that converts PDFs into structured records with strict schema validation, confidence-based retries, and a human review UI. Demonstrates strong practical judgment around making LLM systems reliable in enterprise workflows, including custom orchestration, observability, and continuous evals rather than relying on off-the-shelf abstractions.”

Sarthak Chauhan

Screened

Junior Software Engineer specializing in AI-powered backend and full-stack systems

San Francisco Bay Area, CA2y exp

“Built production AI agents at HubSpot for sales teams, including Next Best Action, Deal Risks, and Deal Plans. Combines frontend React/TypeScript implementation with backend prompt engineering, evaluation in Braintrust, caching, and generation pipeline work, and has experience shipping fast with beta feedback and gated rollouts.”

“Industrial AI/ML practitioner with experience deploying real-time monitoring and anomaly detection in a regulated Sanofi vaccine manufacturing facility, including root-cause workflows, logging/alerting, and SOP-aligned validation—achieving ~90% faster anomaly detection. Also built Python/NLP-style automation to accelerate instrumentation & control documentation (~40% faster) and delivered end-to-end predictive analytics for an agri-food operations/distribution client using close operator and leadership feedback loops.”

“FinTech/AI engineer who has shipped an end-to-end discrepancy-detection product for financial managers using Next.js, FastAPI/GraphQL, Pinecone, and AWS (with dev/staging/prod, observability, A/B testing, and documentation). Also built an AI-native “AI Genesis” system with agentic cyclic workflows, routing, and tool use, and has experience modernizing legacy systems via the strangler fig pattern while coordinating with senior stakeholders on a 5G autonomous simulation platform.”

Ayush Gupta

Screened

Mid-level AI Engineer specializing in Agentic AI and Generative AI

6y exp

“Built and deployed a live LLM-powered platform that takes a LinkedIn job URL + resume and generates job-specific resumes and personalized outreach at scale, with production-grade logging/monitoring/retries on Vercel + Railway. Experienced with agent orchestration (AWS Bedrock/Strands, LangGraph, CrewAI) and rigorous AI workflow testing, plus stakeholder-facing prototypes like data lineage/metadata and NL-to-SQL + dashboard generation.”

“Full-stack engineer with fintech and AI product experience: built HuddleAI end-to-end on Firebase/React, including a serverless LLM meeting-intelligence pipeline (FFmpeg + Google Speech-to-Text + GPT-4 with schema validation) and Slack notifications. At Gemini, owned a Postgres/Scala workflow change for wire deposit approvals that cut blocked registrations by 60% and emphasized correctness/compliance in UK/EU transaction-state UI.”

“ML engineer with production experience across healthcare and fraud domains, including end-to-end ownership of a telecare patient deterioration system at Oracle Health and a GPT-4/RAG fraud reporting solution at Cognizant. Stands out for combining scalable data/ML infrastructure, clinical NLP, and GenAI delivery with measurable gains in model quality and workflow efficiency.”

“Built and shipped a production LLM-powered internal developer tool that accelerated code reviews by about 30% while maintaining reliability through modular orchestration, validation, and monitoring. Demonstrates strong practical depth in agent architecture, backend workflow orchestration, and observability for non-deterministic AI systems, with concrete examples of reducing agent errors by 60%.”

“Backend/ML systems engineer with experience at SDSC, UCSD, and Media.net, building production semantic dataset/model discovery using embeddings + Solr KNN and LLM-based intent/reranking at 5M+ dataset scale. Emphasizes offline/online separation for predictable serving, has delivered measurable gains (23% retrieval accuracy, 38% latency reduction) and helped secure a $3M+ NSF grant.”

“Data Analyst at U.S. Cellular who built production LLM solutions, including a Tableau-embedded chatbot that converts natural language questions into Oracle SQL and returns actionable KPI insights for non-technical users. Also authored MAD-CTI, a multi-agent LLM system for dark web hacker forum threat intelligence (published in IEEE Access) that outperformed single-agent approaches by 14%.”