Vetted Workflow Orchestration Professionals

“Built and deployed a production RAG-based multi-agent chatbot during an internship to help consultants answer client questions and guide users through new IT systems with step-by-step instructions. Demonstrates hands-on experience with LangGraph/LangChain/Google ADK, unstructured document parsing and chunking for RAG, and a reliability-first approach to agent workflows (metrics, fallbacks, human-in-the-loop, guardrails).”

“Senior data engineer with experience in both healthcare (CVS Health) and financial services (Bank of America), building large-scale Azure lakehouse pipelines (30+ EHR sources, ~5TB) and real-time streaming services (Event Hubs/Kafka) for patient vitals. Strong focus on reliability and data quality (Great Expectations, monitoring/alerting, schema drift automation), with measurable outcomes like 50% runtime reduction and 99%+ uptime for regulatory reporting pipelines.”

“Data/Backend engineer with experience at Naukri building large-scale analytics products over a 130M+ user base, including Spark/Airflow pipelines and Kafka-based clickstream validation with Confluent Schema Registry. Also built an audience segmentation backend (Athena/S3 + Spring Boot APIs) for non-technical internal teams and recently shipped a GenAI customer data audit system (FastAPI/Postgres/Llama) that cut sales-planning validation from ~3 months to ~1 week.”

Atulya Bist

Screened

Junior Data Scientist / Software Engineer specializing in LLM analytics and robotics

Los Angeles, CA3y exp

“Robotics/ML engineer who implemented TD3 and PPO in PyTorch to solve the challenging OpenAI Gymnasium humanoid-v5 MuJoCo task, including custom networks, rollout logic, and training scripts. Also has hands-on robotics coursework experience with ROS-based RRT motion planning on a real robotic arm, plus practical CI/CD and containerization experience (Docker, Jenkins, GitHub Actions). Currently exploring world models (VAE + sequence generator) using Euro Truck Simulator data.”

Nagarjuna Vaddineni

Screened

Mid-level Full-Stack Software Engineer specializing in cloud-native microservices and data pipelines

Seattle, WA6y exp

“Amazon backend engineer who built and operated high-scale Java Spring Boot microservices on AWS (EKS/EC2) handling millions of daily transactions, with deep experience debugging p95 latency and database/ORM bottlenecks. Shipped an AI-driven real-time personalization feature by integrating SageMaker model inference end-to-end with low-latency caching and graceful fallbacks, and designed robust order/payment orchestration with retries, compensations, and DLQ-based escalation.”

Sai Dinesh Pusapati

Screened

Senior AI/ML Engineer specializing in GenAI agents and LLM workflows

San Francisco, CA6y exp

“LLM/AI engineer with production experience building a retrieval-based document intelligence system that extracts information from PDFs/emails, backed by Python + Spark pipelines. Focused on reliability and cost/latency optimization (caching, batch processing) and has hands-on orchestration experience with Airflow (sensors, retries, alerts). Also partnered with business stakeholders to deliver customer feedback classification/summarization for faster sentiment insights.”

Harsh Sanas

Screened

Intern-level Software Engineer specializing in GenAI, RAG, and backend systems

San Francisco, CA2y exp

“AI/LLM engineer focused on shipping production-grade agents that automate support, sales intake, and ERP-connected workflows. Stands out for combining strong orchestration and guardrails with measurable business outcomes, including 45% faster support handling, ~$1.2M annual savings, 18% higher customer satisfaction, and 99.5%+ reliability in production.”

“Built a production B2C behavioral interview system for job seekers using LangGraph/LangChain on AWS Bedrock with Nova models, plus a FastAPI backend and Vercel AI SDK frontend. Stands out for practical agent reliability work: local stress testing, OpenTelemetry-to-Datadog observability, token/cost monitoring, and guardrails to keep conversations on track and resistant to instruction override.”

Akhil Kunala

Screened

Mid-level Software Engineer specializing in backend systems and cloud-native FinTech

Seattle, WA5y exp

“Amazon engineer with 5+ years of experience who built an AI-assisted log investigation and triage workflow that cut debugging time by about 30% during on-call incidents. Combines observability tooling like CloudWatch and Splunk with Python, prompt engineering, and RAG-based diagnostics, and has practical experience orchestrating agentic AI workflows with a strong human-in-the-loop reliability focus.”

“LLM/agent engineer who has shipped multiple autonomous, multi-step agents to production (document-to-SOP conversion, test generation, code generation) using a custom Python DAG orchestrator with persistent state, tool-calling permissions, and structured outputs (Pydantic/JSON Schema). Demonstrates strong production hardening practices—semantic contracts, golden-dataset prompt regression tests, circuit breakers, and multi-level monitoring—and delivered large productivity wins (34 hours of manual writing reduced to ~20 minutes review; ~15–20 engineering hours/week saved).”

Vedant Kharwal

Screened

Intern AI/ML Engineer specializing in Generative AI and applied machine learning

Mumbai, India1y exp

“New graduate with hands-on LLM work building a RAG pipeline (HNSW, lexical reranking/boosting, ReAct) and optimizing it through ablation to dramatically reduce latency. Also building a modular personal assistant with a custom wake word model, router-driven agent selection, and integrations like Spotify with secrets managed via .env.”

“Built Baioniq, an enterprise LLM platform for automating extraction from massive unstructured documents like contracts and insurance claims. They demonstrate unusually strong production depth in agentic AI—scaling to 100k+ requests/day, processing 1M+ claim documents, and improving extraction accuracy through rigorous RAG architecture, evaluation, and fallback design.”

“ML engineer with production experience at PayPal and Flipkart, owning high-scale systems across fraud detection, recommendations, and LLM tooling. Stands out for combining strong modeling judgment with practical platform engineering, delivering measurable impact like 22% fewer fraud false positives, 18% CTR lift, 40% less LLM manual review, and 30% faster redeployments.”

“Backend/AI workflow engineer with PayPal experience building workflow-driven financial compliance systems (Python/Java, Postgres, AWS/EKS) at thousands of executions/day. Has shipped production LLM-powered document extraction with strict schema/rule validation, auditability, and human-in-the-loop fallbacks, and has deep expertise in reliability (idempotency, locking, state machines) and Postgres performance tuning.”

“Built and shipped a production enterprise RAG knowledge assistant that returns grounded, cited answers and uses confidence-based fallbacks (clarifying questions/abstention) with monitoring and compliance controls for sensitive data. Implemented end-to-end agent orchestration (function calling, structured JSON, state, retries/rate limits) plus eval/feedback loops, and achieved a reported 30–40% improvement in knowledge-task completion time while reducing hallucinations via retrieval improvements.”

“Built and shipped production LLM agents that automate document processing and decision workflows, with a strong focus on reliability, guardrails, and measurable business impact. Stands out for combining RAG, tool calling, evals/monitoring, and ERP integration to deliver 30-35% manual effort reduction and higher throughput without additional headcount.”

“Walmart engineer who built and shipped a production LLM+RAG system to automate triage and analysis of computer support chats/tickets, producing grounded, schema-constrained JSON outputs for summaries, urgency, and routing recommendations. Emphasizes reliability (hallucination control, confidence thresholds, human-in-the-loop) and runs end-to-end pipelines with Airflow and AWS-native orchestration, plus rigorous evaluation and monitoring tied to business KPIs.”

“Built and shipped a production LLM-powered RAG assistant for enterprise internal document search (PDFs, knowledge bases, structured data), addressing real-world issues like noisy documents, hallucinations, and latency with grounded prompting, retrieval-confidence fallbacks, and performance optimizations. Also partnered with compliance and business teams at JPMc to deliver a solution aligned with regulatory constraints, supported by monitoring, feedback loops, and systematic evaluation.”

“ML/LLM engineer who has shipped a production transformer-based document understanding system on AWS, owning the full pipeline from domain fine-tuning to Dockerized CI/CD deployment. Demonstrates strong production rigor—latency optimization (distillation/quantization, async batching, autoscaling), orchestration with Airflow/Step Functions/Azure Data Factory, and monitoring/drift detection—plus experience translating ops stakeholder needs into adopted AI automation via dashboards.”

Geetha Sri Kasu

Screened

Mid-level Software Engineer specializing in Java/Spring Boot, Kafka, and AWS

5y exp

“Software engineer who owned an end-to-end self-service reporting workflow (secure APIs, async/batched processing, and React UI), improving report generation performance by ~30–40% and reducing manual support effort. Also built a RAG/embeddings prototype over internal docs and service logs with grounding-focused guardrails, and has a strong reliability/observability mindset (retries, DLQs, CI/CD validation, dashboards/tracing) for distributed workflows.”