Help build the AI platform and the agents that run on it, focusing on engineering reliability, cost, latency, and security within regulated enterprise environments.
Compensation
$60–80K depending on experience
Responsibilities
Build features in the LLM gateway: routing, caching, rate limits, per-customer model rules, and cost tracking.
Build parts of the agent runtime: how agents start, run, hold state, and get versioned and rolled back.
Build MCP servers for tools and data, hosted inside the customer's boundary, with scopes and security handled properly.
Build and extend the AI registry: models, agents, prompts, tools, and datasets, with owners, versions, and approval state.
Own the observability architecture for the AI platform, build and operate observability tooling, and enable customers to monitor AI agents and platform performance.
Compensation
Salary: 60-90K+StocKoption
Responsibilities
Own the observability architecture for the AI platform: logs, traces, metrics, and AI-specific signals, end to end.
Stand up and operate LangSmith and related tools inside the customer's environment, and integrate them with the customer's existing observability stack.
Instrument the platform and the agents with OpenTelemetry: traces of agent reasoning, LLM calls, tool and MCP calls, and retrieval steps, with consistent semantic conventions across services.
Build the OTel collector pipelines: collection, processing, sampling, redaction of sensitive data, and export to the right backends, within the customer's data-handling rules.
Build the tooling around observability: SDK helpers and decorators so engineers get tracing for free, dashboards for cost, latency, token usage, and quality, alerting on error rates and spend, and reports an audit team can read.
Own observability for the AI platform, focusing on logs, traces, and metrics for AI agents running in regulated enterprise environments.
Compensation
60-90K+StocKoption
Responsibilities
Own the observability architecture for the AI platform: logs, traces, metrics, and AI-specific signals, end to end.
Stand up and operate LangSmith (and related tools such as Langfuse or Arize Phoenix where they fit) inside the customer's environment, and integrate them with the customer's existing observability stack.
Instrument the platform and the agents with OpenTelemetry: traces of agent reasoning, LLM calls, tool and MCP calls, and retrieval steps, with consistent semantic conventions across services.
Build the OTel collector pipelines: collection, processing, sampling, redaction of sensitive data, and export to the right backends, within the customer's data-handling rules.
Build the tooling around observability: SDK helpers and decorators so engineers get tracing for free, dashboards for cost, latency, token usage, and quality, alerting on error rates and spend, and reports an audit team can read.
Own the observability architecture for the AI platform, build and operate tools, and enable customers to see AI operations.
Compensation
Salary: 60-90K+StocKoption
Responsibilities
Own the observability architecture for the AI platform: logs, traces, metrics, and AI-specific signals, end to end.
Stand up and operate LangSmith (and related tools such as Langfuse or Arize Phoenix) inside the customer's environment, and integrate them with the customer's existing observability stack.
Instrument the platform and the agents with OpenTelemetry: traces of agent reasoning, LLM calls, tool and MCP calls, and retrieval steps, with consistent semantic conventions across services.
Build the OTel collector pipelines: collection, processing, sampling, redaction of sensitive data, and export to the right backends, within the customer's data-handling rules.
Build the tooling around observability: SDK helpers and decorators so engineers get tracing for free, dashboards for cost, latency, token usage, and quality, alerting on error rates and spend, and reports an audit team can read.
Own the end-to-end architecture of the AI platform: gateway, agent runtime, MCP layer, skills and asset registry, retrieval, evals, observability, identity, and governance.
Compensation
160-180k + 25k Bonus + Stock Options (Based on experience and match to the role)
Responsibilities
Own the end-to-end architecture of the AI platform: gateway, agent runtime, MCP layer, skills and asset registry, retrieval, evals, observability, identity, and governance.
Design how agents run on Kubernetes: packaging, scheduling, scaling, isolation, networking, state and memory, versioning, promotion, and rollback.
Design the AWS foundation the platform sits on: EKS, IAM, networking, private endpoints, and infrastructure-as-code, built for a regulated enterprise with restricted egress.
Define the identity model for agents: how an agent authenticates as itself, acts on behalf of a user without gaining more access than that user has, and leaves an audit trail.
Define the developer experience: how a developer in the customer's organization goes from an idea to a deployed agent, with the right guardrails and the least friction.
Own the end-to-end architecture of an AI platform for a large financial services enterprise, designing components, infrastructure, and developer experience, and presenting to client stakeholders.
Compensation
Salary: 160-180k + 25k Bonus + Stock Options (Based on experience and match to the role)
Responsibilities
Own the end-to-end architecture of the AI platform: gateway, agent runtime, MCP layer, skills and asset registry, retrieval, evals, observability, identity, and governance.
Design how agents run on Kubernetes: packaging, scheduling, scaling, isolation, networking, state and memory, versioning, promotion, and rollback.
Design the AWS foundation the platform sits on: EKS, IAM, networking, private endpoints, and infrastructure-as-code, built for a regulated enterprise with restricted egress.
Define the identity model for agents: how an agent authenticates as itself, acts on behalf of a user without gaining more access than that user has, and leaves an audit trail.
Define the developer experience: how a developer in the customer's organization goes from an idea to a deployed agent, with the right guardrails and the least friction.
Own the end-to-end architecture of an AI platform for a large financial services enterprise, designing components, infrastructure, and governance, and presenting to client stakeholders.
Compensation
Salary: 160-180k + 25k Bonus + Stock Options (Based on experience and match to the role)
Responsibilities
Own the end-to-end architecture of the AI platform: gateway, agent runtime, MCP layer, skills and asset registry, retrieval, evals, observability, identity, and governance.
Design how agents run on Kubernetes: packaging, scheduling, scaling, isolation, networking, state and memory, versioning, promotion, and rollback.
Design the AWS foundation the platform sits on: EKS, IAM, networking, private endpoints, and infrastructure-as-code, built for a regulated enterprise with restricted egress.
Define the identity model for agents: how an agent authenticates as itself, acts on behalf of a user without gaining more access than that user has, and leaves an audit trail.
Define the developer experience: how a developer in the customer's organization goes from an idea to a deployed agent, with the right guardrails and the least friction.
Lead a team of engineers to build and ship an AI platform for a large financial services enterprise.
Compensation
Salary: 100-125K+Stock Options
Responsibilities
Lead a team of 3–5 engineers: break down the work, set priorities with the architect and the CEO, review code, and keep delivery on track.
Write production code across the platform: the LLM gateway, the agent runtime, MCP servers, the skills and asset registry, evals, and the APIs developers use to deploy agents.
Design and build the APIs and services the platform exposes, in Python, with the habits of a production engineer: tests, observability, clean interfaces, clear error handling.
Build the developer-facing parts of the platform (CLI, SDK, or web UI) so an engineer at the customer can go from an idea to a deployed agent without asking us.
Own code quality: set the coding standards, the review process, the test strategy, and the CI/CD pipeline, and hold the team to them.
Lead a team of engineers to build and ship an AI platform for a large financial services enterprise, designing APIs, services, and deployment pipelines in Python and AWS.
Lead a team of 3–5 engineers building an AI platform for a large financial services enterprise, focusing on reliability, cost, latency, and security.
Compensation
100-125K+Stock Options
Responsibilities
Lead a team of 3–5 engineers: break down the work, set priorities with the architect and the CEO, review code, and keep delivery on track.
Write production code across the platform: the LLM gateway, the agent runtime, MCP servers, the skills and asset registry, evals, and the APIs developers use to deploy agents.
Design and build the APIs and services the platform exposes, in Python, with the habits of a production engineer: tests, observability, clean interfaces, clear error handling.
Build the developer-facing parts of the platform (CLI, SDK, or web UI) so an engineer at the customer can go from an idea to a deployed agent without asking us.
Own code quality: set the coding standards, the review process, the test strategy, and the CI/CD pipeline, and hold the team to them.