Lead AI Engineer

Salary: $68,000 - 108,000 per year Requirements:

• Experience architecting and delivering multiple production-grade generative AI or conversational AI products end to end, including at least one taken from concept to production on a tight timeline.
• Experience working within consulting or client teams in fast-paced environments with ambiguous scope, weekly demos, and exposure to senior stakeholders.
• Experience leading AI product discovery and requirements workshops, translating business goals into use cases, conversation flows, user stories, and measurable success criteria.
• Strong hands-on Python development and infrastructure-as-code experience with CDK, Terraform, or CloudFormation.
• Experience delivering production chatbots or virtual assistants with multi-turn context, intent handling, session memory, human handoff, and multichannel delivery across web, mobile, messaging, or contact centers.
• Experience designing high-concurrency chatbot systems in production; candidates should be able to describe peak concurrent users, p95 latency, and daily conversation volume.
• Knowledge of scale engineering, including response streaming, provisioned throughput and quota planning, semantic and response caching, load testing, autoscaling, and graceful degradation under model rate limits.
• Experience designing RAG pipelines, including chunking, embeddings, hybrid search, reranking, metadata filtering, vector stores such as OpenSearch, pgvector, Aurora, or Pinecone, and groundedness evaluation.
• Essential: AWS Bedrock experience, including foundation model selection, Knowledge Bases, Guardrails, Agents, model evaluation, and cost optimization.
• Essential: AWS Bedrock AgentCore experience with Runtime, Memory, Gateway, Identity, and Observability for secure, large-scale agent deployment and operation.
• Experience designing MCP servers and clients that expose enterprise APIs and data as governed tools, including authentication and authorization.
• Knowledge of A2A and multi-agent orchestration patterns, such as supervisor, hierarchical, and peer-to-peer, using frameworks such as Strands Agents, LangGraph, or CrewAI.
• Strong foundations in AWS architecture, including serverless, containers, networking, IAM, and security, as well as distributed systems and API design.
• Knowledge of responsible AI practices, including guardrails, hallucination control, prompt-injection defense, auditability, and data privacy in regulated environments.
• Experience with LLM observability and evaluation tools such as Langfuse, Ragas, or Bedrock evaluations, or similar.
• Based in or willing to relocate to Atlanta; US work authorization is required.

• Lead discovery workshops with business and technical stakeholders, map user journeys and conversation flows, capture functional and non-functional requirements, and create a prioritized backlog with clear acceptance criteria.
• Define the products target architecture early, covering conversational AI, RAG, and agents on AWS Bedrock and Bedrock AgentCore.
• Design assistants that support thousands of concurrent users with predictable latency, cost, and uptime.
• Architect agent ecosystems using MCP for tool and data access and A2A for agent collaboration.
• Drive iterative delivery from a working MVP through hardening and load testing to production readiness.
• Build alongside the team, developing agent code, prompts, retrieval pipelines, integrations with data platforms and enterprise systems, and infrastructure as code.
• Establish LLMOps standards for evaluation, prompt and model versioning, observability, guardrails, and cost governance.
• Own non-functional design, including security, identity and access, PII handling, compliance, resilience, and disaster recovery.
• Shape scope and trade-offs with stakeholders, lead weekly demos, and present architecture and progress to client leadership.
• Run design reviews, mentor engineers, and provide a documented, operable platform—including runbooks, architecture decisions, and a cost model—at the end of the engagement.

• AI
• API
• AWS
• OpenSearch
• Architect
• Embedded
• IAM
• Support
• LLM
• Langfuse
• MCP
• Mobile
• Python
• RAG
• Security
• Serverless
• Terraform
• Web
• Cloud

More:

We are DTS, and we are seeking a Lead AI Engineer for a direct-client engagement based in Atlanta, Georgia. The role works closely with the client team to build a conversational AI product on AWS in a fast-paced environment, with an accelerated path from concept to production. The engagement is embedded with the client team and combines architectural leadership with hands-on engineering.

last updated 40 week of 2026