AI Solution Architect (Gen AI / ML Platforms)

Role Overview

We are seeking a highly experienced AI Solution Architect to design and deliver enterprise-grade AI/ML and Generative AI solutions at scale.

This is a hands-on leadership role focused on building production-ready AI systems, architecting modern GenAI platforms, and enabling engineering teams through robust developer platforms and best practices.

You will work at the intersection of AI engineering, platform architecture, and developer experience, driving innovation while ensuring reliability, scalability, and governance.

What You ll Do

Architect & Deliver AI/GenAI Solutions

• Design and implement scalable AI/ML and Generative AI solutions in production environments
• Build advanced RAG (Retrieval-Augmented Generation) and GraphRAG pipelines
• Develop and orchestrate AI agents with capabilities such as tool usage, memory, and multi-agent collaboration
• Design and publish reusable plugins, tools, and AI skills for internal developer ecosystems

LLM Engineering & Orchestration

• Work deeply with Claude ecosystem (Claude API, system prompts, context management)
• Implement LLM orchestration using frameworks such as LangChain, LangGraph, Semantic Kernel, or AutoGen
• Optimize prompt design, context windows, and model interactions for performance and accuracy
• Conduct structured LLM evaluations (RAGAS, LangSmith, custom evaluation pipelines)

Observability, Monitoring & Evaluation

• Build observability for distributed AI systems using Datadog, Dynatrace, OpenTelemetry, PrometheGrafana
• Implement AI-specific monitoring, including:
  • LLM tracing
  • hallucination detection
  • token usage and cost tracking
  • latency and drift monitoring
• Design evaluation frameworks to measure quality, safety, relevance, and groundedness at scale
• Manage logging and search using ELK Stack or AWS OpenSearch

Engineering & Platform Development

• Develop high-quality backend systems using:
  • Python (FastAPI, async programming)
  • .NET / C# (ASP.NET Core, middleware, DI)
• Build and manage APIs (REST, GraphQL) with proper versioning and governance
• Design event-driven systems using Kafka (streaming, schema management, consumer groups)
• Create CI/CD pipelines using GitHub Actions (reusable workflows, secrets, OIDC)

AWS Cloud Architecture

• Architect AI solutions using AWS Bedrock (agents, guardrails, knowledge bases)
• Work across core AWS services: EKS, Lambda, API Gateway, S3, DynamoDB, RDS/Aurora, SQS/SNS
• Implement secure and scalable cloud environments using:
  • IAM, KMS, VPC design, PrivateLink
• Build infrastructure using Terraform or AWS CDK
• Optimize cost and performance of AI workloads (FinOps mindset)

Developer Platform & Enablement

• Build and scale Internal Developer Platforms (IDPs) with self-service capabilities
• Define golden paths for AI development and deployment
• Enable developer productivity through tooling, automation, and platform standards
• Promote DevSecOps practices, including SAST/DAST and secure software supply chains

Leadership & Stakeholder Engagement

• Lead and mentor cross-functional engineering teams (15+ members)
• Collaborate with product, security, compliance, and architecture teams
• Present AI strategies, roadmaps, and outcomes to executive leadership (VP/C-suite)
• Drive adoption of AI platforms across large engineering organizations
• Stay hands-on: contribute code, review PRs, and guide architecture decisions

What We re Looking For

• 5+ years of hands-on experience building AI/ML and GenAI solutions in production
• Strong expertise in:
  • RAG / GraphRAG architectures
  • AI agents and orchestration frameworks
  • Prompt engineering and LLM optimization
• Experience with vector databases (Pinecone, pgvector, Azure AI Search)
• Deep understanding of distributed systems and microservices
• Strong programming skills in Python and/or .NET
• Experience with AWS cloud architecture and services
• Proven track record in observability, monitoring, and evaluation of AI systems

Nice to Have

• Experience with Cursor AI and AI-assisted development workflows
• Familiarity with InnerSource and platform adoption strategies
• Exposure to DORA metrics and engineering productivity frameworks