Contact

C. James Ekhator

AI/ML Platform Engineer

Shipping production AI and cloud infrastructure. Multi-model LLM orchestration on AWS Bedrock. Regulated-workload experience from JPMorgan Chase (SOX) and Quality Health Care Group (HIPAA).

Scroll To View More

What started as Java debugging in a college coffee shop became 6+ years shipping production systems. I build backend services in Python and Java, cloud infrastructure on AWS, and multi-model LLM architectures on Bedrock, with the guardrails, cost budgets, and observability that hold up under real traffic. My instinct is toward systems that operate themselves and AI that ships to real users, not demos.

LinkedIn Profile
GitHub profile

Professional Experience

Two tenures across regulated workloads: SOX-compliant banking at JPMorgan Chase and HIPAA-compliant healthcare at Quality Health Care Group.

JPMorgan Chase & Co.

Software Engineer (Banking)

April 2024 - Present

Platform engineering across private and public cloud for SOX-regulated banking services. Jenkins, Spinnaker, Terraform, AWS (Lambda, ECS, Step Functions), Cloud Foundry.

  • Architected agentic AI workflow + chat dashboard on Amazon Bedrock and JPMC's CDAO Smart SDK, with autonomous Jira ticket completion via job-type-routed agents (extensible across Grafana, SonarQube, ServiceNow integrations) with extended-thinking validation, plus a developer console surfacing cross-repo context, SEAL/FID credentials, entitlements, and regulatory information through knowledge-base-grounded LLM queries
  • Architected blue-green deployment strategy with automated database migration rollbacks for zero-downtime releases across SOX-regulated banking services
  • Designed end-to-end CI/CD pipelines (Jenkinsfile + Spinnaker + custom Git branching) supporting ~1-hour production lead time for backend Django and Java/Spring services
  • Engineered Celery + RabbitMQ async task processing with multi-layer health-check endpoints for proactive incident detection
  • Built backend API routes via Django views and DRF serializers, extending banking services with new endpoints under RBAC + SOX-aligned access controls
  • Built large-scale data processing pipelines on AWS EMR, Kinesis, Glue, and Athena, supporting real-time and batch analytics for cross-team consumers
  • Provisioned AWS Lambda, ECS tasks, and Step Functions workflows with Terraform (IaC), automating cross-account event handling via EventBridge and SNS alerting
  • Integrated PyTest integration test suite as CI/CD quality gate over Django banking-service routes, blocking deployments on regression

Quality Health Care Group Inc.

Software Engineer (Healthcare)

June 2018 - April 2024

Sole-developer build of HIPAA-aligned healthcare platform. Django REST Framework + React/TypeScript → Cloud Build (19-step CI/CD) → GCP/AWS.

  • Architected HIPAA-aligned healthcare platform end-to-end (Django REST API + React/TypeScript) and built a 19-step Cloud Build CI/CD pipeline with automated rollback management and distributed locking, eliminating concurrent-deploy race conditions
  • Engineered JWT authentication with RBAC across 4 clinical role tiers (Nurse, Supervisor, Admin, Support), token rotation, blacklisting, and comprehensive audit trails with 7-year retention for HIPAA compliance

Multi-Model Routing

Side project exploring cost/latency tradeoffs across 2026's Bedrock lineup: Claude Sonnet 4.6, Opus 4.7, Haiku 4.5, Nova 2 Pro, Nova 2 Lite. Pattern carried over from the production multi-model router I built for the Healthcare Compliance Platform (Bedrock Claude + Titan), which cut monthly inference costs 78% on HIPAA-regulated healthcare document processing. Select a scenario to see how routing decisions play out for different request shapes.

Select a use case to see the orchestration pattern.

Selected projects

Healthcare Compliance Platform: production GenAI on HIPAA infrastructure. Arc Modality: multi-tenant AI infrastructure built as independent R&D. Plus earlier social-media + cloud work at Xoobug.

Healthcare Compliance Platform logo
Healthcare Compliance Platform

Bedrock / HIPAA / Full Stack

Production GenAI platform for HIPAA-regulated healthcare compliance. AI capabilities shipped:

  • Multi-model Bedrock routing (Claude + Titan tiers) with auto-fallback + token budgeting; 78% inference cost reduction
  • 12+ production prompts: chain-of-thought, few-shot examples, prompt injection guardrails
  • Real-time AI chat with 11 diagnostic tools via LLM function calling + SSE streaming
  • Multimodal document OCR extracting structured JSON from 14 healthcare form types
  • Computer vision with Rekognition Video for Q15 patient monitoring
  • NLP-based PHI protection via Comprehend Medical
  • Chain-of-thought compliance engine evaluating documents vs PA BHRS + CMS guidelines (4-category weighted scoring)
  • Semantic search via pgvector (1024-dim) + audio dictation → structured data pipeline

Certifications & Credentials

Currently pursuing the AWS Certified Generative AI Developer Professional cert; target June 2026.

AWS Certified Generative AI Developer Professional

In Progress, target June 2026

Exam code AIP-C01. Covers foundation models, multi-model orchestration, Bedrock integration patterns, prompt engineering, RAG architectures, responsible AI, and production GenAI deployment.

AWS exam details →