Senior AI Agent Platform Engineer

Embedded Shishya; United States; Remote; USD 120,000 - 190,000; Full time

Job summary

STARLIMS is seeking an experienced software engineer to advance its agent platform and runtime. You will design planning/execution loops, tool calls, and durable execution, grounding decisions in enterprise data and enabling safe, auditable agent behavior.

Join a team focused on reliability, observability, and end-to-end control of non-deterministic systems in regulated environments. Remote collaboration and AWS-based deployment are anticipated as core parts of the role.

Qualifications

• 6+ years of software engineering experience including production systems.
• Experience building production LLM systems, including tool-using or multi-step agentic workflows beyond simple prompting and chat interfaces.
• Strong understanding of LLM behavior, limitations, and failure modes in multi-step runs.
• Experience with LLM APIs, tool calling, and planning/execution loops.
• Expertise in backend and cloud engineering (AWS or equivalent).
• Proficiency in TypeScript and/or Python.

Responsibilities

• Design and build the runtime agents execute on: planning/execution loops, tool calling, state management, and durable execution.
• Build the layer through which agents reach platform data and external systems safely.
• Coordinate, delegate, and handoff across agents/workflows; ensure versionability and testability.
• Ground agent decisions with authoritative data and include human-in-the-loop with approval gates.
• Create evaluation harnesses for multi-step behavior and define production metrics.
• Implement guardrails, timeouts, and observability across agent runs.

Skills

6+ years software engineering

Production LLM systems

LLM APIs & tool calling

Backend & cloud (AWS)

TypeScript/Python

Tools

OpenAI

Anthropic

MCP protocols

Embeddings & vector search

Terraform

Jest/Playwright/pytest

AWS Lambda/Step Functions

Job description

STARLIMS is seeking an experienced software engineer to advance its agent platform and runtime. You will design planning/execution loops, tool calls, and durable execution, grounding decisions in enterprise data and enabling safe, auditable agent behavior.

Join a team focused on reliability, observability, and end-to-end control of non-deterministic systems in regulated environments. Remote collaboration and AWS-based deployment are anticipated as core parts of the role.