Gen AI Engineer

Job Description

Gen AI Engineer

Location:

Remote, but twice quarterly travel to our HQ in Rochester, NY (Company paid) for team meetings.

Employment:
Full time W2

Innovative Solutions is a Premier Tier AWS Partner delivering cloud and Generative AI solutions for SMB, startup, and enterprise customers. Our GenAI practice builds production-ready solutions using Amazon Bedrock, vector databases, LLM orchestration, and custom AI agents across healthcare, financial services, and technology.

We’re looking for a GenAI Engineer to join our Professional Services team, building and deploying real-world Generative AI applications. You’ll work directly with customers to design, implement, and scale AI-powered solutions including conversational assistants, RAG systems, document automation, and intelligent data platforms.

• Design and build production Generative AI applications using Amazon Bedrock (Claude, Nova, Llama)
• Develop RAG pipelines using vector databases (Weaviate, Open Search, Pinecone, Chroma, FAISS)
• Build AI agents and multi-agent workflows using Lang Chain, Llama Index, Bedrock Agents, or custom frameworks
• Implement prompt engineering, embeddings, and fine-tuning strategies
• Create serverless AWS architectures using Lambda, API Gateway, Step Functions, Event Bridge
• Build REST and Web Socket APIs using FastAPI or Flask
• Design data ingestion, ETL/ELT pipelines, and semantic search systems
• Implement observability, logging, and performance optimization for AI workloads
• Collaborate with clients and internal teams in an agile delivery model

• Amazon Bedrock (model invocation, streaming, guardrails)
• Python (3.9+) including async, testing frameworks (pytest)
• LLM integration (Anthropic, OpenAI, Cohere)
• Vector databases for semantic search
• Lang Chain, Llama Index, or agent orchestration frameworks
• AWS Serverless:
  Lambda, API Gateway, Step Functions
• Infrastructure as Code:
  Cloud Formation, CDK, or Terraform

• Bedrock Agent Core, Dynamo
  
  DB, Docker/ECS, AWS Glue
• RAG architecture optimization and embedding models
• Cloud Watch, IAM, CI/CD pipelines
• Sage Maker, Open Search, Event Bridge, Web Sockets
• Experience in regulated industries (HIPAA, PCI, SOC
  2)

• 5+ years of software engineering experience
• 2+ years building on AWS in production
• 1+ years hands-on Generative AI experience (LLMs, RAG, agents)
• Strong client-facing communication and problem-solving skills

• Conversational AI assistants using Bedrock and Claude
• RAG-based document intelligence platforms
• AI-powered data extraction and validation systems
• Multi-agent workflow automation
• Voice and personalization solutions using AWS AI services