AI Architect Conversational & Agentic AI

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., You will work closely with a client team in Atlanta to design and build a conversational AI product on AWS in a fast-paced environment. You will lead requirement gathering with business and technical stakeholders, own the end-to-end architecture, make fast technical calls, and stay hands-on so the team moves from concept to a production-ready release on an accelerated timeline. You are equally comfortable at a whiteboard with client leadership and in a code review with engineers.

What you will do

• Lead requirement gathering: run discovery workshops with business and technical stakeholders, map user journeys and conversation flows, capture functional and non-functional requirements, and turn them into a prioritised backlog with clear acceptance criteria.
• Define the target architecture for the product early and decisively conversational AI, RAG and agents on AWS Bedrock/Bedrock AgentCore.
• Design chatbots and assistants that can serve thousands of concurrent users with predictable latency, cost and uptime.
• Architect agent ecosystems using MCP for tool and data access and A2A for agent-to-agent collaboration.
• Drive rapid, iterative delivery: get to a working MVP quickly, then harden, load test and take the product to production readiness.
• Build hands-on alongside the team: agent code, prompts, retrieval pipelines, integrations with data platforms and enterprise systems, and infrastructure as code.
• Set standards for LLMOps: evaluation, prompt and model versioning, observability, guardrails and cost governance.
• Own non-functional design: security, identity and access, PII handling, compliance, resilience and disaster recovery.
• Work as part of the client team: shape scope and trade-offs with stakeholders, run weekly demos and present architecture and progress to client leadership.
• Run design reviews, mentor engineers and hand over a documented, operable platform (runbooks, architecture decisions, cost model) at the end of the engagement.

Must have

• Enterprise delivery: architected and delivered multiple production-grade GenAI or conversational AI products end to end, including at least one taken from concept to production on a tight timeline.
• Embedded, fast-paced delivery: worked as part of consulting or client teams; comfortable with ambiguous scope, weekly demos and senior stakeholder exposure.
• Requirements and discovery: led discovery and requirement workshops for AI products; able to translate business goals into use cases, conversation flows, user stories and measurable success criteria.
• Hands-on builder: writes production Python and infrastructure as code (CDK, Terraform or CloudFormation) not a diagram-only architect.
• Conversational AI: production chatbots or virtual assistants with multi-turn context, intent handling, session memory, human handoff and multichannel delivery (web, mobile, messaging, contact centre).
• Chatbot scale: designed systems running at high concurrency in production. Candidates should state peak concurrent users, p95 latency and daily conversation volume they handled.
• Scale engineering: response streaming, provisioned throughput and quota planning, semantic and response caching, load testing, autoscaling and graceful degradation under model rate limits.
• RAG: retrieval pipeline design chunking, embeddings, hybrid search, reranking, metadata filtering, vector stores (OpenSearch, pgvector, Aurora, Pinecone or similar) and groundedness evaluation.
• AWS Bedrock (essential): foundation model selection, Knowledge Bases, Guardrails, Agents, model evaluation and cost optimisation.
• Bedrock AgentCore (essential): Runtime, Memory, Gateway, Identity and Observability for deploying and operating agents securely at scale.
• MCP: designed MCP servers and clients that expose enterprise APIs and data as governed tools, including authentication and authorisation.
• A2A and multi-agent: orchestration patterns (supervisor, hierarchical, peer-to-peer) using A2A and frameworks such as Strands Agents, LangGraph or CrewAI.
• Foundations: strong AWS architecture (serverless, containers, networking, IAM, security), distributed systems and API design; Python hands-on.
• Responsible AI: guardrails, hallucination control, prompt-injection defence, auditability and data privacy 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 design, user feedback loops and A/B testing of prompts or flows.
• AWS Certification on AI/GenAI
• Domain experience in Finance

5 10 years overall, 3+ in GenAI/Agentic AI, * 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, 10-15 years overall, 5+ in GenAI/Agentic AI