Senior AI Engineer — Conversational & Agentic AI

About the role:

You will work closely with a client team in Atlanta to build a conversational AI product on AWS in a fast-paced environment. You own major components end to end, turn the architecture into production-quality code, and help the team move from concept to a production-ready release on an accelerated timeline. You are comfortable demoing to client stakeholders and leading technical work for less experienced engineers.

What you will do:

•          Build the core of the product — conversational AI, RAG and agents on AWS Bedrock/Bedrock AgentCore — working closely with the AI Architect.

•          Implement chatbot features: multi-turn conversation flows, session memory, tool calling, streaming responses and human handoff.

•          Build RAG pipelines: 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: ship a working MVP quickly, then harden, optimise and load test it for production.

•          Engineer for scale: tune latency, throughput and cost so the chatbot holds up under thousands of concurrent users.

•          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: estimate and break down work, join weekly demos and explain technical trade-offs to stakeholders.

•          Review code, mentor engineers and contribute to runbooks and technical documentation for handover.

Must have:

•          Enterprise delivery: built and shipped at least two production-grade GenAI or conversational AI applications, with ownership of significant components, including one delivered on a tight timeline.

•          Embedded, fast-paced delivery: worked as part of consulting or client teams; comfortable with ambiguous scope, weekly demos and stakeholder exposure.

•          Hands-on engineering: strong production Python and REST APIs

•          Conversational AI: built production chatbots or virtual assistants with multi-turn context, intent handling, session memory, human handoff and multichannel delivery (web, mobile)

•          Chatbot scale: worked on chatbots running at high concurrency in production. Candidates should state peak concurrent users, p95 latency and their part in scaling it.

•          Scale engineering: response streaming, semantic and response caching, retries and rate-limit handling, provisioned throughput, autoscaling and load testing.

•          RAG: implemented retrieval pipelines with vector stores (OpenSearch, pgvector, Aurora, Pinecone or similar) and measured retrieval quality and groundedness.

•          AWS Bedrock (essential): model invocation and selection, Knowledge Bases, Guardrails, Agents and model evaluation.

•          Bedrock AgentCore (essential): hands-on with Runtime, Memory, Gateway, Identity and Observability to deploy and operate agents.

•          MCP: built MCP servers and clients, including authentication and authorisation for tools.

•          A2A and multi-agent: built multi-agent workflows using A2A and frameworks such as Strands Agents, LangGraph or CrewAI.

•          AWS foundations: Lambda, API Gateway, ECS or EKS, DynamoDB, S3, IAM, VPC networking and CloudWatch.

•          Responsible AI: guardrails, hallucination control, prompt-injection defence and PII handling in regulated environments.

•          LLM observability and evaluation: Langfuse, Ragas, Bedrock evaluations or similar tools to trace, monitor and evaluate LLM applications.

•          Location: based in or able to relocate to Atlanta; US work authorisation required.

Nice to have:

•          Voice AI with Amazon Connect, Lex or speech models.

•          Equivalent platforms on Azure OpenAI, Vertex AI or Databricks Mosaic AI.

•          Fine-tuning, distillation or small-model deployment for cost and latency.

•          Product mindset: conversational UX, user feedback loops and A/B testing of prompts or flows.

•          Front-end chat UI experience (React).

•          AWS Certification on AI/GenAI

•          Domain experience in Finance