YOUR Why

Join our client as a Senior Automation Engineer and help shape the future of GenAI innovation for the bank. In this role, you’ll build cutting-edge AI solutions that transform unstructured data into powerful insights, design embedding & retrieval pipelines using advanced LLMs, and develop scalable, production-ready GenAI applications. You’ll collaborate in a fast-paced, highly innovative environment where creativity is encouraged, experimentation is celebrated, and your ideas can directly influence how AI evolves across the organization. If you’re passionate about pushing the boundaries of what’s possible with AI, this is your opportunity to make an impact.

How YOU Will Spend YOUR Days

• Design/implement ingestion & transformation workflows for unstructured content (e.g., PDFs, reports, emails), incorporating chunking, semantic tagging, & metadata enrichment to support GenAI & semantic search applications.

• Develop & manage embedding services utilizing advanced LLMs (e.g., Anthropic, Meta, Mistral) & ensure optimal storage & semantic retrieval of vectorized data with solutions (e.g., OpenSearch, FAISS, AWS Kendra, Azure AI Search).

• Build & manage LLM-driven information extraction & Retrieval-Augmented Generation (RAG) pipelines via AWS Bedrock models, Knowledge bases, & agents.

• Develop & maintain interactive user interfaces (UIs) using React or Streamlit to facilitate seamless user engagement.

• Create GitOps automation workflows (e.g., Terraforms, GitHub Actions, ArgoCD) to enable application deployment processes.

• Collaborate with engineering, product, & data teams to prototype & scale GenAI services, establishing robust patterns & frameworks that underpin future machine learning & artificial intelligence capabilities at the bank.

What YOU Bring

• 3+ years of hands-on experience with GenAI/ML infrastructure, including designing & building embedding services, vector databases (e.g., FAISS, Weaviate, OpenSearch), & RAG architectures.

• Experience processing & transforming unstructured data (e.g., PDFs, reports, knowledge bases) into AI-ready formats, including semantic chunking, metadata enrichment, & content classification.

• Experience integrating hosted LLM services via AWS Bedrock, Azure AI Foundry, or similar platforms, as part of production-ready applications.

• Proven track record in building & operationalizing GenAI solutions that integrate with LLMs, including prompt engineering strategies/adapter-based fine-tuning techniques (e.g., LoRA, PEFT) to align model behavior with domain-specific use cases.

• Extensive experience with CI/CD & GitOps workflows (e.g., GitHub Actions, ArgoCD), infrastructure-as-code (e.g., Terraform), & Kubernetes-based deployments (especially AWS EKS).

Location: Hybrid (2 days/week) position based in Denver, CO, but remote candidates based in the Chicago, IL or Minneapolis, MN areas will also be considered. For remote candidates, this role may require occasional travel to Denver.

Compensation: 80.00 - 85.00 per hour W2 / 3-month contract

No third parties: no C2C or sponsorship available