Job Summary
The Lead AI Engineer will work closely with a client team in Atlanta to build a conversational AI product on AWS in a fast-paced environment. The role will own major components end to end, turn architecture into production-quality code, and help the team move from concept to a production-ready release on an accelerated timeline. The ideal candidate will be comfortable demonstrating solutions to client stakeholders and leading technical work for less experienced engineers.

Key Responsibilities
• Build the core of the product, including conversational AI, RAG, and agents on AWS Bedrock and Bedrock AgentCore, working closely with the AI Architect.
• Implement chatbot features including multi-turn conversation flows, session memory, tool calling, streaming responses, and human handoff.
• Build RAG pipelines including document ingestion, chunking, embeddings, hybrid search, reranking, metadata filtering, and source citation.
• Develop MCP servers that expose enterprise APIs and data as governed tools, and integrate agents with each other using A2A.
• Drive rapid, iterative delivery by shipping a working MVP quickly and then hardening, optimizing, and load testing it for production.
• Engineer for scale by tuning latency, throughput, and cost so the chatbot can support high-concurrency usage.
• Build evaluation suites for answer quality, groundedness, and regression testing of prompts and models.
• Ship through CI/CD with infrastructure as code, logging, tracing, alerting, and cost monitoring.
• Work as part of the client team to estimate and break down work, participate in weekly demos, and explain technical trade-offs to stakeholders.
• Review code, mentor engineers, and contribute to runbooks and technical documentation for handover.

Required Qualifications
• 10+ years of professional experience.
• Experience building and shipping at least two production-grade Generative AI or conversational AI applications, with ownership of significant components, including one delivered on a tight timeline.
• Experience working as part of consulting or client teams, with the ability to work with ambiguous scope, weekly demos, and stakeholder exposure.
• Strong hands-on production Python and REST API development experience.
• Experience building production chatbots or virtual assistants with multi-turn context, intent handling, session memory, human handoff, and multichannel delivery across web and mobile.
• Experience working on chatbots running at high concurrency in production, with the ability to provide peak concurrent users, p95 latency, and details of contributions to scaling.
• Experience with response streaming, semantic and response caching, retries and rate-limit handling, provisioned throughput, autoscaling, and load testing.
• Experience implementing RAG pipelines with vector stores such as OpenSearch, pgvector, Aurora, Pinecone, or similar technologies, including measuring retrieval quality and groundedness.
• Essential experience with AWS Bedrock, including model invocation and selection, Knowledge Bases, Guardrails, Agents, and model evaluation.
• Essential hands-on experience with Bedrock AgentCore, including Runtime, Memory, Gateway, Identity, and Observability for deploying and operating agents.
• Experience building MCP servers and clients, including authentication and authorization for tools.
• Experience building multi-agent workflows using A2A and frameworks such as Strands Agents, LangGraph, or CrewAI.
• Experience with AWS services including Lambda, API Gateway, ECS or EKS, DynamoDB, S3, IAM, VPC networking, and CloudWatch.
• Experience implementing responsible AI practices including guardrails, hallucination control, prompt-injection defense, and PII handling in regulated environments.
• Experience with LLM observability and evaluation tools such as Langfuse, Ragas, Bedrock evaluations, or similar technologies.

Preferred Qualifications
• Experience with Voice AI using Amazon Connect, Lex, or speech models.
• Experience with equivalent AI platforms such as Azure OpenAI, Vertex AI, or Databricks Mosaic AI.
• Experience with fine-tuning, distillation, or small-model deployment for cost and latency optimization.
• Product mindset with experience in conversational UX, user feedback loops, and A/B testing of prompts or flows.
• Front-end chat UI development experience using React.
• AWS certification related to AI or Generative AI.
• Experience in the finance domain.