Apply Now

Key Responsibilities

• Architect, build, and own end-to-end Agentic AI solutions on AWS — from design through production deployment.
• Lead and mentor a cross-functional Scrum team of engineers, ML practitioners, and data specialists.
• Define technical standards, code-review practices, and engineering best practices for the team.
• Design and implement RAG pipelines, LLM-powered agents, and multi-agent orchestration frameworks.
• Drive cloud architecture decisions: serverless, microservices, containers (ECS/EKS), and data services on AWS.
• Collaborate with Product Owners to translate business requirements into robust technical solutions.
• Actively participate in sprint ceremonies — planning, stand-ups, retrospectives — as the technical authority.
• Establish CI/CD pipelines, infrastructure-as-code (IaC), and automated testing strategies.
• Evaluate and integrate emerging AI tools, models, and frameworks into the product roadmap.
• Ensure security, scalability, observability, and cost-efficiency of all cloud-based AI workloads. 

Required Expertise

• AWS Full-Stack Engineering
  • Hands-on experience with core AWS compute, storage, networking, and AI/ML services.
  • Lambda, ECS/EKS, EC2, API Gateway, S3, RDS, DynamoDB, Bedrock, SageMaker, Step Functions
  • IAM, VPC, CloudWatch, CloudFormation / CDK / Terraform
  • Proven ability to design resilient, highly available, and cost-optimised architectures (Well-Architected Framework).
  • CI/CD implementation using CodePipeline, GitHub Actions, or equivalent tooling.
• Artificial Intelligence, RAG & Agents
  • Practical experience with LLM integration (OpenAI, Anthropic Claude, AWS Bedrock, Mistral, or similar).
  • Design and deployment of Retrieval-Augmented Generation (RAG) pipelines at scale.Embedding models, vector stores (Pinecone, pgvector, OpenSearch, Weaviate), chunking strategies
  • Building autonomous and multi-agent systems using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or Amazon Bedrock Agents.
  • Prompt engineering, chain-of-thought reasoning, tool/function calling, and agent memory management.
  • Evaluation, monitoring, and observability of AI systems (hallucination detection, latency, cost tracking).
• Python Development
  • Expert-level Python for backend services, data processing, and AI/ML workflows.
  • Proficiency with key libraries: FastAPI / Flask, Pydantic, asyncio, boto3, LangChain / LlamaIndex.
  • Strong software engineering fundamentals: clean code, SOLID principles, unit and integration testing.
• Experience supporting project-to-operations transition in onsite, client-facing environments
• Based in Houston, TX with the ability to work out of the Woodside client site

Must Have Capabilities

• AWS Architecture 
• Python Expert        
• LLM Integration     
• RAG Pipelines        
• Agent Frameworks
• CI/CD & IaC            
• Scrum / Agile Leadership     
• API Design               
• Cloud Security       
• Production AI Systems
• Demonstrable hands-on delivery (not just oversight) of AI-powered, cloud-native applications.
• Strong execution discipline with experience in tracking deliverables, managing competing priorities, and ensuring quality outcomes
• Strong communication skills to bridge technical depth with business stakeholders.
• Track record of delivering production systems within Agile sprints.

Nice to Have

• Experience with AWS Bedrock Agents, Knowledge Bases, or Guardrails.
• Knowledge of fine-tuning or RLHF for domain-specific LLM adaptation.
• Familiarity with graph databases (Neptune) or knowledge graphs for agent reasoning.
• Frontend experience (React, Next.js) for full-stack ownership of AI-powered interfaces.
• Data engineering background: Glue, Athena, Redshift, or Spark.
• Exposure to MLOps practices and tooling (MLflow, W&B, SageMaker Pipelines).
• AWS certifications: Solutions Architect Professional, Machine Learning Specialty.
• Contributions to open-source AI / ML projects.
• Experience with multi-modal AI (vision, speech, embeddings beyond text).

Ideal Profile

The successful candidate is a builder at heart — someone who moves fluidly between whiteboard architecture and writing production code. They are naturally curious about the AI landscape, stay ahead of rapidly evolving agent frameworks, and bring a pragmatic engineering mindset that turns experimentation into reliable, scalable products.

• 10+ years of software engineering experience, with at least 3–5 years in cloud-native AWS environments.
• 2+ years of hands-on work with LLMs, RAG, or autonomous AI agents in a production context.
• Prior experience leading technical delivery within a Scrum or scaled-Agile (SAFe) team.
• A portfolio or demonstrable examples of AI-powered products shipped to production.