About The Position

TribalScale is seeking a developer to build and operate shared, cloud-native agent infrastructure on AWS for an AI-assisted modeling pipeline and internal AI-enabled development workflows. The client builds virtual Arm devices—including phones, IoT boards, and automotive controllers—that run unmodified firmware on its CHARM hypervisor. Its Atlas product supports virtual IoT, automotive, and embedded hardware. The modeling pipeline collects vendor documentation, extracts peripheral specifications, generates register and system definitions, synthesizes behavioral C code, and validates results by booting vendor firmware. It is used for internal bring-ups and by Atlas partners to build and validate their own models. The role is part of the AI & SDLC Platform team, which provides agent infrastructure and AI platform support to delivery teams. Model Delivery owns the modeling backlog and outcomes; this role owns the infrastructure the pipeline runs on, including orchestration, multi-model inference, evaluation, observability, and secure deployment. The goal is to turn an engineer-run prototype into a reliable, measurable service and apply the same infrastructure to AI-enabled internal software development workflows. The position involves collaboration with client and TribalScale teams, product teams responsible for customer-facing MCP and API surfaces, and cross-functional delivery partners. The successful candidate will help turn evolving requirements into executable plans, deliver reliable AI-enabled products, establish measurable evaluation and observability practices, and create reusable technical patterns. Occasional travel for client workshops or on-site delivery may be required.

Requirements

  • Hands-on experience with AWS services including Bedrock, Lambda, ECS or EKS, S3, and Step Functions.
  • Experience with GenAI infrastructure, including LLM integration, agent frameworks, MCP, semantic caching, and LLM evaluation.
  • Familiarity with Amazon EKS and Kubernetes-based deployments.
  • Familiarity with GitHub or GitLab workflows, secrets management, and secure deployment practices.
  • Knowledge of observability tools such as Datadog and log aggregation strategies.
  • Ability to write clean, maintainable code and contribute to shared documentation and best practices.
  • Experience collaborating directly with customers, stakeholders, or cross-functional delivery teams.
  • Excellent written and verbal communication skills, including the ability to explain AI-system behavior, limitations, risks, and technical trade-offs clearly.
  • Comfort working in fast-moving environments where requirements and technical constraints continue to evolve.
  • A high degree of ownership, curiosity, empathy, and bias toward action.
  • Ability to travel occasionally for client workshops or on-site delivery, where required.

Nice To Haves

  • Hands-on experience with agentic AI frameworks such as LangChain, LangGraph, CrewAI, or AutoGen.
  • Experience optimizing AI workloads using Amazon Bedrock, SageMaker, or other AWS AI/ML services.
  • Experience integrating and managing multiple LLM providers, including OpenAI, Anthropic Claude, and open-source models.
  • Familiarity with AI-assisted development tools such as Claude Code, Cursor, or GitHub Copilot.
  • Experience with LLM evaluation and observability tools such as LangSmith, Langfuse, or Arize Phoenix.
  • Exposure to Arm architectures, firmware development, IoT devices, hypervisors, or hardware virtualization.
  • Experience building MCP servers, integrating external tools, or developing reusable agent tooling.
  • Experience with distributed systems, Kubernetes, container orchestration, and scaling production AI workloads.
  • Experience automating software development processes, including code generation, automated testing, code reviews, and CI/CD workflows.
  • Contributions to open-source AI frameworks, developer tools, or cloud infrastructure projects.

Responsibilities

  • Design and implement orchestration for long-running agent pipelines on AWS, including job orchestration, artifact and manifest generation, checkpointing, retries, and prompt and model versioning.
  • Run multi-model inference across Amazon Bedrock and self-hosted models, with routing, an independent judge model, semantic caching, and token-cost and latency controls.
  • Provide shared evaluation and tracing hooks so Model Delivery can measure pipeline stages and compare models, prompts, and pipeline versions.
  • Build and operate the internal AI gateway, agent runtime, and tool integrations used by engineers in AI-enabled software development workflows, including code review, ticket-to-merge-request workflows, and knowledge retrieval.
  • Develop and maintain CI/CD pipelines and infrastructure as code using Terraform or CDK, with secure secrets management and least-privilege access.
  • Instrument agents and pipelines for success rate, cost, latency, and failure modes, and maintain dashboards, alerts, and runbooks.
  • Work with product teams that own customer-facing MCP and API surfaces to keep internal agent tools and product interfaces consistent.
  • Turn loosely defined client needs into clear, executable technical plans.
  • Establish evaluation and observability practices that make quality measurable and regressions visible.
  • Improve agent behavior by refining harnesses, loops, tools, graphs, context, and safeguards.
  • Help client teams understand AI-system capabilities, limitations, failure modes, and responsible operation.
  • Create reusable technical patterns that accelerate future TribalScale engagements.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service