Vetted API Development Professionals

“Built production LLM systems including a real-time customer feedback analysis and workflow automation platform using RAG and multi-agent orchestration with confidence-based human escalation, addressing privacy and legacy integration challenges. Also automated ML operations with Airflow/Kubernetes (e.g., daily churn model retraining) cutting retraining time to under 30 minutes, and demonstrates a rigorous testing/monitoring approach plus strong non-technical stakeholder collaboration.”

“Built and shipped a production Chrome extension (Promptly) that lets users select text on any webpage and transform it in place (rewrite/shorten/translate) using on-device AI plus external LLMs. Implemented a custom lightweight orchestration layer for prompt chaining, context flow, and output validation, and tackled tricky browser Selection API issues to preserve formatting while keeping the UX simple and fast.”

“Engineering/technology leader who spearheaded an ultra low-latency AI-CDN SaaS platform on a multi-cloud stack (AWS/Azure/Alicloud), helping transform ARHT from a boutique provider into a global SaaS solution. Built distributed engineering and follow-the-sun support teams and helped secure major enterprise clients (TD Bank, Gucci, NATO, EY) while also leading board communications and raising $6M for a public-listed company.”

“ML/GenAI engineer with recent CVS Health experience building a production RAG system over unstructured financial/research documents using LangChain, FAISS, and Pinecone, plus LoRA/PEFT fine-tuning of GPT/LLaMA for domain-aware summarization. Demonstrates strong applied MLOps and data engineering skills (Airflow/Prefect, Docker/Kubernetes, CI/CD, MLflow) and measurable impact (sub-second retrieval, ~40% better context retrieval, ~25% entity matching improvement).”

“Built and deployed a compliance-sensitive LLM pipeline that extracts rebate logic from hospital–supplier medical contracts, using multi-layer redaction (regex/NER/dictionary), schema-validated structured outputs, and secure placeholder reinsertion. Hosted models on Amazon Bedrock to avoid retraining on sensitive data and improved both accuracy and cost by splitting the workflow into a lightweight section classifier plus a fine-tuned extraction model, orchestrated with LangChain and evaluated via layered, test-driven agent assessments.”

“Built a production multimodal LLM system (Gemini on GCP) to automate behavioral coding of family-involved science experiment videos, including preprocessing for inconsistent lighting/audio and LangGraph-orchestrated parallel workflows. Also developed rubric-based AI grading workflows and partnered closely with non-technical education stakeholders through explainability-focused walkthroughs and manual-vs-AI evaluation alignment.”

“Built and deployed a production-style vision-language pipeline that generates structured medical reports from chest X-rays using BioViLT embeddings, an image-text alignment module, and BiGPT fine-tuned with LoRA, delivered via Streamlit and hosted on AWS EC2. Also collaborating experience presenting EDA findings, feature importance, and model performance to Ford managers while working with vehicle parts data at Bimcon.”

“Backend engineer with fintech/banking experience (e.g., Canara Bank) building secure Python/Flask microservices for financial reporting and unified data access. Strong in Postgres/SQLAlchemy performance optimization (including materialized views) and in productionizing ML services on AWS (Lambda/ECS/CloudWatch) with Docker, model registries, and blue-green deployments, plus multi-tenant isolation via JWT-based middleware.”

“Operations-focused advisor/consultant with experience helping a fast-growing e-commerce company scale internal operations and customer experience. Implemented a CX playbook, cloud CRM, and real-time risk controls (order tracking + anomaly detection), delivering 30%+ CSAT improvement and up to 25% retention lift in six months while also building a foundational compliance program to support regulatory and investor readiness.”

“Product-leaning full-stack engineer (65% product / 35% infra) who built core components of the LightFoot feature flag platform: end-to-end client/server SDKs with OpenTelemetry-based observability and a React+TypeScript UI for flag management and metrics dashboards. Strong focus on performance (memoization/lazy loading/caching), reliable API design, and Postgres modeling for read-heavy flag evaluation workloads, with AWS production experience (EC2/ECS/Lambda/API Gateway/VPC).”

“Backend/Founding-Engineer-style builder who architected AESOP, a multi-agent distributed platform for biomedical literature evidence synthesis. Implemented an async FastAPI stack on AWS with LangGraph orchestration, Redis/Postgres+pgvector, and Celery-based background processing, plus defense-in-depth security (JWT refresh/rotation and DB-level isolation). Notable for hardening LLM workflows with multi-layer validation and convergence safeguards to prevent hallucinations and infinite agent loops.”

“Backend engineer with hands-on experience designing and refactoring scalable Node.js/MongoDB systems and building Python/FastAPI services. Emphasizes production-grade security (JWT, refresh tokens, RBAC, Supabase Auth, RLS) and reliability practices like strong testing, monitoring, and rollback planning, including resolving concurrency and token/validation edge cases.”

“Backend engineer with experience at HSBC and Machinations who has delivered major production performance wins (cutting large trade-file upload times from ~13–15s to ~2s) using chunked parallel processing with strong reliability controls. Also built and shipped an applied AI RAG workflow using Langflow + Cohere embeddings + FAISS with hosted/local LLM fallbacks (Hugging Face, Ollama) and production-grade guardrails, observability, and evaluation.”

“Backend/data engineer with hands-on production experience building FastAPI APIs secured with JWT and delivering AWS-based data processing solutions using Lambda and ECS Fargate. Has worked with Snowflake/third-party API sources and targets including DynamoDB, S3, RDS, Redshift, and Glue, and uses CloudWatch/X-Ray for monitoring and troubleshooting. Seeking ~$65/hr and is open to onsite work in Bethesda, MD.”