• Contribute to the design and development of AI agents integrated into live production systems • Help build and maintain benchmark datasets to evaluate agent performance, accuracy, and safety • Design and refine prompts, tool integrations, and agent workflows • Implement, test, and optimize services and tooling across the stack — backend, data, scripting, automation, and glue code • Collaborate closely with senior engineers on system design, multi-agent orchestration, and deployment • Participate in code reviews, debugging, and documentation to ensure best practices • Work in a team environment that encourages mentorship, knowledge sharing, and hands-on learning

• Develop artificial intelligence software in support of the Department of Commerce • Design and develop AI models, algorithms, and applications • Collaborate to preprocess and analyze large datasets • Implement machine learning and deep learning algorithms • Documenting code, algorithms, and processes

• Own the technical vision, architecture, and solution standards across all engagements within the account • Drive the consolidation of multiple concurrent projects into a single coordinated build motion • Set the technical direction the engineering team builds to • Partner with the Program Manager on sequencing, dependencies, and burn tracking • Serve as the trusted technical partner and primary technical point of contact for client executive stakeholders • Operate as a senior solution architect on active build work

• Design and evolve conversational agents in production at high volume, with WhatsApp as the primary channel • Orchestrate multi-agent systems: intent routing, handoff, session management, memory and failure recovery • Develop tools and MCP servers that connect agents to the business domain • Instrument LLM observability (Langfuse / LangSmith / OpenTelemetry): cost, latency, tool-call rate and production quality • Build and maintain automated evals — no prompt or model change goes live without measurement • Integrate multiple LLM providers (OpenAI, Anthropic, Groq) with fallback strategies and cost controls • Implement RAG pipelines (embeddings, pgvector, reindexing) • Create and maintain Claude Code skills, subagents and workflows that automate the delivery cycle • Ensure reliability: rate limiting, durable queues, anti-bot guardrails, error tracking • Operate agents on Kubernetes: GitOps deployments, resources, metrics and manifests • Collaborate with product and design during discovery