Vetted Model Fine-tuning Professionals

“Backend/data engineer who built a production-ready multi-agent financial intelligence system (Mycroft) that orchestrates specialized AI agents to analyze real-time market data using FastAPI and Pinecone vector search. Brings strong security/reliability instincts (rate limiting, JWT/OAuth2, retries/backoff, health checks) and has caught high-impact data integrity issues in financial migrations (timezone normalization across global legacy systems).”

“ML/LLM engineer with production experience building medical RAG systems to automate chart review, including retrieval + re-ranking and rigorous evaluation. Notably uncovered errors/bias in physician-curated ground truth by tracing answers back to source note chunks and presented evidence to an academic partner, accelerating deployment. Also built a RAG-based FAQ chatbot for a health insurance company and delivered it to non-technical stakeholders via demos.”

“Built and deployed Clyra.AI, an AI-driven daily scheduling product that uses a LangGraph-based multi-agent LLM pipeline (task extraction, verification, reflection) grounded with strict RAG over emails/documents/calendars and real-world signals like health metrics. Designed a custom agent orchestrator with bounded loops/termination conditions and a self-auditing verification/reflection layer to reduce hallucinations while controlling latency and cost via caching and model distillation.”

“Built and shipped “LabMate,” a production AI assistant specialized in laboratory hardware, using a weighted multi-source RAG pipeline with reranking and reasoning-focused query decomposition to handle complex user questions. Deployed on a local GPU cluster with vLLM and NVIDIA MPS (plus OCR/VLM components), and established evaluation using synthetic + public reasoning datasets while collaborating weekly with non-technical admins to align requirements and resource constraints.”

“Built production AI/RAG-style systems for message Q&A and insurance claims workflows, combining data ingestion, indexing/retrieval, and LLM integration with fallback modes. Has hands-on orchestration experience (Airflow, Prefect, LangChain) and cites large operational gains (claims processing reduced to ~45 seconds; manual review -50%; false alerts -30%) through automated, monitored pipelines and close collaboration with non-technical stakeholders.”

“LLM/agent builder who shipped a live consumer AI-agent app (kalpa.chat) that visualizes complex reasoning as interactive graphs and abstracts multi-provider model usage via a unified wallet. Professionally has applied LangChain/LangGraph to IVR parsing and to scaling a football video-generation pipeline at DAZN, including shipping a VAR-specific retrieval/order fix via SQL after iterating with a non-technical PM.”

“Built and shipped a production LangGraph-based multi-agent LLM analytics/decision copilot that answers questions across SQL/BI systems and unstructured docs, emphasizing grounded, tool-verified outputs with citations and confidence gating. Deep hands-on experience with orchestration (LangGraph, CrewAI, OpenAI Assistants, MCP) plus real-world latency/cost optimization (vLLM batching/KV caching, speculative decoding, quantization) and rigorous eval/observability. Partnered closely with business/ops stakeholders to deliver explainable reporting automation, cutting manual reporting time by 50%+.”

“Built and deployed LLM-powered agentic chatbot and text-to-SQL systems using LangGraph/LangChain (and Bedrock), structuring workflows as DAGs with planning/replanning and validation to improve tool-calling reliability and reduce hallucinations. Operates production feedback loops with online/offline metrics, drift detection, and LangSmith-based evaluation pipelines, and regularly partners with business stakeholders and clinicians using slide decks and visual charts.”

“AI Engineer Co-Op at Northeastern University who built a production Patient Persona Chat Bot to help nursing students practice clinical interactions, fine-tuning Llama 3 and integrating a LangChain + Pinecone RAG pipeline deployed on Amazon Bedrock. Emphasizes clinical accuracy and reliability with guardrails, retrieval filtering, and continuous evaluation, and also brings strong data engineering/orchestration experience (Airflow, EMR/PySpark, ADF, dbt, Databricks, Snowflake).”

“LLM engineer who built and productionized a system to classify GitHub commits (performance vs non-performance) using zero-/few-shot approaches over commit messages and diffs, working at ~5M-record scale on multi-node NVIDIA GPUs. Experienced orchestrating end-to-end LLM pipelines with Airflow and GitHub Actions, and emphasizes reliability via testing, guardrails, and observability while collaborating closely with non-technical product stakeholders.”

“AI engineer with production experience building a LangGraph-based, stateful multi-agent system at MetLife to automate complex insurance claims adjudication, integrating document discovery, Azure Document Intelligence OCR/extraction, and health data analysis. Strong in agent orchestration and production deployment (Docker + FastAPI REST APIs), with a structured approach to reliability, evaluation, and stakeholder-driven requirements.”

“LLM engineer who built a production-style educational questionnaire generation system (MCQs/fill-in-the-blanks/short answers) using Hugging Face models (BERT/T5) and implemented grounding, decoding tuning, and post-generation validation to control hallucinations and quality. Also developed a "tech care" assistant chatbot with a custom Python orchestration/router layer (intent classification, context management, multi-step flows) and a structured testing/evaluation approach including expert review and automated checks.”

“Founding/early engineer experience across Asante and a Series A startup (Adgency), shifting from data science/ML into owning production full-stack systems end-to-end. Built core product flows (registration, business profiles, map service), AWS-deployed gRPC microservices with CI/CD, and operated low-latency agent/video ad generation workflows with retries/fallbacks and PostHog-based observability.”

“GenAI/NLP engineer with experience building classification and summarization pipelines in PyTorch and deploying multimodal GPT-4-style workflows. Has integrated LLM applications across OpenAI, Azure OpenAI, and Amazon Bedrock, and uses LangChain/LlamaIndex/Semantic Kernel to orchestrate RAG and agent workflows with production-focused evaluation metrics like task success rate and groundedness.”

“Built and shipped a production agentic LLM analytics platform that lets non-SQL business users query relational databases in plain English via a RAG + LangChain/LangGraph workflow and FastAPI service. Emphasizes safety and reliability with guardrails (validation/access control), testing/evaluation frameworks, and performance optimization (caching, monitoring, Dockerized scalable deployment), reducing dependency on data teams and speeding analytics turnaround.”

“ML/NLP engineer with healthcare and industrial IoT experience: built an Optum pipeline that converted 2M+ physician notes into structured entities and linked them with claims/pharmacy data to create an actionable patient timeline. Deep hands-on expertise in production NER, entity resolution, and hybrid search (Elasticsearch + embeddings/FAISS), plus robust data engineering practices (Airflow, Spark, data contracts, auditability) and experimentation-to-production rollout via shadow mode and feature flags.”

“Machine learning/NLP engineer with deep Azure stack experience (Data Factory, Databricks/Spark, Delta Lake, Azure OpenAI, Azure AI Search) who built end-to-end production systems for semantic clustering, entity resolution, and hybrid search. Demonstrated measurable gains from embedding fine-tuning (~15% retrieval precision, ~10–12% nDCG@10) and designed scalable, quality-checked pipelines with MLOps best practices.”

“ML/AI engineer who deployed a real-time, edge-based computer-vision pipeline for produce recognition in retail self-checkout to reduce shrink. Demonstrates strong end-to-end production chops: multi-camera data calibration/sync, ranking-based modeling for fine-grained classes, latency-focused optimization, and continuous A/B testing/monitoring with guardrails. Experienced with ML orchestration (Kubeflow Pipelines, Airflow) and CI/CD via GitHub Actions, and collaborates closely with store operations to make interventions usable in the checkout flow.”

“Built a production LLM/RAG document analysis system for large financial documents (credit reports/PDFs) to help business analysts extract insights faster. Implemented end-to-end pipeline orchestration with LangChain, vector search (e.g., FAISS), and hallucination controls (context grounding, similarity thresholds, and no-answer fallback), delivered as a Dockerized Python API.”

“Built Hexagon’s production Text-to-CAD Copilot that converts text and rough sketches into editable CAD code, combining GraphRAG (Neo4j/LangChain) with a Gemini-powered vision module and multi-agent geometric validation—cutting manual modeling from a day to ~45 seconds and driving retrieval latency below 50ms. Also has large-scale GCP data/ML orchestration experience (Airflow/Cloud Composer, Dataflow, Pub/Sub, Snowflake) processing 50M+ daily records with drift monitoring and automated reliability controls.”