Skip to content

Satya Kada

Senior AI/ML Engineer & Security Architect | DevSecOps | Cloud Platforms • Des Moines, IA (willing to relocate anywhere in USA) • k*********@gmail.com • +17******032 • drivetube.ai/•••••

Professional Summary

Senior AI/ML Engineer & Security Architect with 9+ years of experience building production Generative AI, RAG and multi-agent systems for regulated enterprises. Proven expertise in architecting agentic platforms and Model Context Protocol (MCP) servers using LangChain and LangGraph, integrating vector search (Pinecone, FAISS, OpenSearch) and hybrid retrieval to eliminate hallucinations. Strong cloud-native background on AWS (ECS/Fargate, Lambda, API Gateway) and Azure OpenAI/Foundry, plus IaC using AWS CDK and Terraform. Deep domain experience in healthcare, insurance and financial services — delivering multi‑terabyte data pipelines, 99.9% production availability, and high-concurrency backends supporting 10k+ daily queries. Skilled in PyTorch/Hugging Face, FastAPI, distributed telemetry (CloudWatch, LangSmith), and identity-aware AI governance (Microsoft Entra ID, OBO). Focused on secure, cost-conscious LLM orchestration and observability at scale.

Technical Skills

Programming Language: Python,SQL
Frontend Technologies: React
Backend Technologies: Pydantic
Databases: OpenSearch
Cloud Platforms: Amazon Web Services,Fargate,Lambda,AWS Glue,Microsoft Azure,CloudWatch
DevOps & Infrastructure: AWS CDK,Terraform,Docker
API & Integrations: Amazon API Gateway,PyTest
Data Analysis & Visualization: Streamlit,Pandas,NumPy,PySpark
AI/ML Frameworks & Libraries: PyTorch,XGBoost,LightGBM
Generative AI & LLMs: LangChain,LangGraph,MCP,LangSmith,MLflow
Vector Databases & RAG: Pinecone
Identity & Access Management (IAM): OIDC,Microsoft Entra ID

Work Experience

Wellmark Blue Cross and Blue Shield
Des Moines, IA
Senior AI/ML Engineer
Feb 2026 – Present
Health insurance — engineered agentic AI and secure model-foundry integrations to connect enterprise systems (GitHub, Jira, ServiceNow) under strict OIDC governance.
Tech Stack: AWS Lambda, Fargate, Amazon OpenSearch, Azure AI Search, LangChain, LangGraph, Microsoft Entra ID, AWS CDK, Terraform
  • Architected an enterprise Agentic AI platform using LangGraph and LangChain to orchestrate multi-step insurance workflows and developer onboarding agents.
  • Developed secure MCP servers to expose schema-scoped enterprise knowledge from GitHub, Jira and internal databases for context-aware agent reasoning.
  • Instrumented hybrid retrieval pipelines combining BM25 lexical candidates with dense embeddings in Amazon OpenSearch and Azure AI Search to improve gateway relevance.
  • Engineered distributed backend patterns using AWS Lambda and EventBridge to offload non-critical tasks from inference paths, reducing end-user request latency by over 30%.
  • Designed a pluggable guardrail framework performing automated PII redaction and prompt security filtering that saved ~20 hours/month of manual audit work.
  • Standardized declarative IaC using AWS CDK and Terraform to provision production Fargate clusters and vector databases, resolving 3 major environment issues pre-production.
  • Implemented identity-aware access using Microsoft Entra ID and OBO flows to enforce RBAC and auditable model invocation across business units.
Epic
Verona, WI
Senior AI/ML Engineer
Jan 2024 – Feb 2026
Healthcare/EHR — built RAG and multi-agent systems to power clinical research and document retrieval from large EHR repositories.
Tech Stack: PyTorch, LangChain, LangGraph, Pinecone, PySpark, AWS Glue, Pydantic, Streamlit, LangSmith, Amazon CloudWatch
  • Engineered a two-stage retrieval and ranking pipeline integrating BM25 candidate generation with a PyTorch cross-encoder, improving top-5 clinical retrieval precision by 28%.
  • Spearheaded migration from keyword search to an enterprise RAG platform using LangChain and Pinecone to process millions of clinical records with high-extraction fidelity.
  • Built an Autonomous Clinical Research Agent with the ReAct framework to query EHR, PubMed and ontologies and to surface evidence for clinicians.
  • Developed PySpark and AWS Glue pipelines to transform multi-terabyte clinical interaction logs into feature sets for ranking models (millions of records processed).
  • Optimized hybrid retrieval by applying Reciprocal Rank Fusion and Cross-Encoder re-ranking to increase RAG precision for long-form clinical documents.
  • Orchestrated a LangGraph-based multi-agent system and session isolation patterns using Pydantic validation to eliminate context bleed across concurrent patient sessions and supported 10,000+ daily clinician queries.
  • Built real-time Streamlit observability UIs and integrated LangSmith and Amazon CloudWatch for step-level tracing and token consumption monitoring.
Barclays
New York, NY
Artificial Intelligence Engineer
Oct 2022 – Jan 2024
Banking / Financial services — transitioned document search to RAG and deployed autonomous research agents for analyst workflows.
Tech Stack: LangChain, Pinecone, Amazon OpenSearch, AWS Glue
  • Spearheaded the migration to an enterprise RAG platform using LangChain and Pinecone to index dense financial filings and large regulatory disclosures.
  • Designed dense vector retrieval workflows benchmarked by Recall@K and MAP that delivered a 75% improvement in search relevance versus legacy lexical systems.
  • Engineered an Autonomous Financial Research Agent leveraging ReAct prompting to query internal market feeds and filings for analyst research.
  • Configured and tuned Amazon OpenSearch clusters with custom n-gram tokenizers and financial synonym dictionaries to optimize lexical recall.
  • Built serverless ETL pipelines with AWS Glue to parse and normalize high-density financial PDFs for downstream vectorization, processing millions of pages.
  • Delivered $800,000+ annual operational savings by automating document ingestion and retrieval workflows while scaling to support large analyst workloads.
Cigna Healthcare International Health (via Randstad)
Machine Learning Engineer
Oct 2021 – Aug 2022
Healthcare compliance — fine-tuned transformer models and built reproducible MLOps pipelines for regulatory document search.
Tech Stack: PyTorch, AWS SageMaker, MLflow, Docker, spaCy
  • Fine-tuned domain-specific Transformer models (BERT, GPT-J) using PyTorch and Hugging Face on AWS SageMaker to produce dense embeddings for medical search.
  • Built scalable NLP preprocessing pipelines for regulatory PDFs using regex tokenization and spaCy lemmatization to create clean training corpora.
  • Containerized end-to-end ML pipelines with Docker and deployed production endpoints on SageMaker with reproducible environments.
  • Established MLflow-based model versioning and artifact tracking to ensure reproducible training and validation against compliance benchmarks.
  • Constructed a structured JSONL dataset of 50,000+ medical QA pairs from thousands of unstructured regulatory PDFs for fine-tuning and evaluation.
  • Implemented validation protocols to eliminate domain-specific hallucinations, achieving a 92% accuracy rate in automated non-compliance detection.
Fiserv (via CTS)
Python Developer
Jan 2018 – Oct 2021
Payments / Financial services — built real-time fraud detection backends and feature pipelines for transaction scoring.
Tech Stack: Python, Pandas, NumPy, SQL, XGBoost
  • Engineered Python back-end services to support real-time fraud detection ingesting and scoring 5,000+ transactions per second.
  • Optimized inference and I/O to achieve sub-50ms end-to-end latency for fraud scoring pipelines.
  • Authored complex SQL (CTEs, window functions) to aggregate historical transaction logs for training dataset curation.
  • Conducted EDA and feature engineering with Pandas and NumPy to produce 100+ high-signal financial features used by ranking models.
  • Trained and deployed gradient-boosted models (XGBoost, LightGBM) for transaction risk ranking and integrated model-drift monitoring scripts to trigger retraining.
  • Automated deployment workflows with custom Python tooling, reducing time-to-production for new predictive services from months to weeks.

Certifications

LLM Engineering Specialization — Udemy / Ed Donner • 2026
Agentic AI & Multi-Agent Systems Specialization — Udemy / Ed Donner • 2026
Production LLMOps & Enterprise Cloud Deployment — Udemy / Ed Donner • 2026

Achievements

  • Claims Guideline Agent — Wellmark Hackathon (selected initiative) — 2026: Architected and led a cross-functional team to deliver a Generative AI MVP demonstrating rapid enterprise value during Wellmark's 2026 hackathon.
  • Tech Tank Webinar — Security Campaigns and AI Usage (Wellmark): Delivered training on integrating GHAS CodeQL, Dependabot and Copilot AutoFix into enterprise CI/CD while optimizing token use across large repositories.

Powered by Drivetube · Create your own profile at drivetube.ai

Explore Drivetube

  • Drivetube Profile — your free digital resume — at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept. Documentation.
  • Free Job Board — verified openings crawled ATS-by-ATS from 100,000+ real company career pages across 35 ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed. Documentation.
  • Job Hunt Program — managed job hunting, a one-time purchase from $199.99. JobScout matches verified roles to your real experience band, Blend AI writes a uniquely tailored resume and cover letter for every application, and the Autofill extension fills the form — or Let Us Apply submits it for you. Documentation.
  • Resume Writing Services — human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile. Documentation.
  • Community Membership — from $4.99/month (₹1,999/year in India). Unlocks the gated job-board filters — visa sponsorship, security clearance, workplace and application time — plus Job-Scout AI matching, Resume Report AI, Interview AI prep sheets, Recruiter Outreach AI sent from your own Gmail, Apply or Skip triage, a daily market feed and a $10,000+ library including 23 ATS-validated resume templates. Documentation.
  • Drivetube Hire — for employers — hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do. Documentation.

Full product documentation — every product explained, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.

The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.