Senior AI Software Engineer (Generative AI / AWS Bedrock) -

About

We are seeking a Senior AI Software Engineer to design and build production‑grade AI applications powered by large language models and foundation models. In this role, you will develop scalable commercial solutions using AWS Bedrock and other AI model providers, integrating advanced AI capabilities into real‑world products and platforms. You will work at the intersection of AI engineering, cloud architecture, and product development, building intelligent systems that leverage multiple foundation models for reasoning, automation, and data‑driven insights. This is a hands‑on role for engineers passionate about transforming cutting‑edge AI capabilities into robust, scalable commercial applications.

Responsibilities

Technology Stack and AI/LLM Programming Expertise

• Hands‑on experience with LLM APIs or foundation models
• Experience building:
  • RAG systems
  • AI copilots
  • Conversational agents
  • Automated workflows
  • AI‑driven analytics
  • Document AI solutions
• Python; Java / TypeScript / Go (any backend language)
• Design and develop production AI applications using models available via AWS Bedrock and external providers:
  • AWS Bedrock (Anthropic Claude, Amazon Titan, Meta Llama, Cohere, OpenAI)
  • OpenAI
  • Open‑source LLMs
• Cloud services & infrastructure: S3, API Gateway, Step Functions, Lambda / ECS / EKS, Docker / Kubernetes, FastAPI, Terraform
• Create pipelines for:
  • Embeddings
  • Document ingestion
  • Knowledge indexing
  • Model evaluation
• Vector databases (pg‑vector, S3‑vector, OpenSearch, FAISS)
• Embeddings and semantic search
• Prompt engineering, tracing, hallucination detection, cost monitoring, prompt performance, drift detection
• Model evaluation frameworks
• Experience with LangChain, LangGraph, LlamaIndex, or AI orchestration frameworks
• LLM monitoring and observability
• Multi‑model routing systems
• Building AI agents or tool‑using LLMs
• Knowledge of AI safety, guardrails, and prompt management
• Deploying models with Docker and Kubernetes (MCP, FastMCP)
• Reinforcement learning
• AWS SageMaker with MLOps
• Bedrock API integration (e.g., from Lambda or other services)
• Design high‑performance AI APIs and microservices
• Optimize latency, reliability, and cost of model inference
• Implement evaluation pipelines and monitoring for AI systems

Required Qualifications

• 6+ years software engineering experience
• 3+ years building AI/ML‑powered applications
• Experience deploying AI systems into production

What We’re Looking For

• Thinks like a systems architect and builder
• Has shipped real AI products to production
• Understands trade‑offs between models
• Can design robust AI pipelines
• Is comfortable working with rapidly evolving AI technologies

Example Problems You’ll Work On

• Build an enterprise knowledge assistant using Bedrock
• Create AI agents that automate complex workflows
• Develop document intelligence pipelines for financial or operational data
• Design multi‑model orchestration frameworks
• Optimize LLM cost, latency, and reliability