STARLIMS Logo

STARLIMS

Software Engineer - Agentic System Development

Posted 22 Days Ago
Remote
Hiring Remotely in United States
Senior level
Remote
Hiring Remotely in United States
Senior level
Build agentic AI platform runtimes and production agents, including planning loops, tool calling, durable execution, retrieval, human approvals, evaluation harnesses, guardrails, observability, and audit trails. Integrate enterprise systems and operate backend services on AWS while improving reliability, security, cost, and traceability of non-deterministic multi-step systems.
The summary above was generated by AI

About the Role: 

We’re building AI into STARLIMS, a platform used across quality manufacturing, life sciences, public health, forensics, and environmental sciences. 

This role is focused on agentic systems: software that reasons over a task, calls tools, works through multiple steps, and hands the result to a person to review and approve. 

Our users work under strict accuracy, traceability, and validation requirements. The engineering challenge is making non-deterministic systems reliable, observable, and controllable enough to be trusted, tested, and shipped. 

You’ll work on both the platform and runtime our agents execute on and the production agents built on top of it. 

What You’ll Work On: 

Agent Platform & Runtime (Core Focus) 

  • Design and build the runtime our agents execute on: planning and execution loops, tool calling, state management, durable execution, and failure recovery 
  • Build the layer through which agents reach platform data and external systems safely 
  • Design coordination, delegation, and handoff across agents and workflows where needed 
  • Make agent behavior versionable, testable, measurable, and regression-safe across releases 
  • Build reusable primitives so new agents are configured rather than rebuilt from scratch 

Building Agents (Core Focus) 

  • Take a domain workflow from expert conversation to a working agent: goals, actions, execution flow, failure handling, and success criteria 
  • Ground agent decisions and outputs in authoritative enterprise data rather than relying on model knowledge alone 
  • Implement human-in-the-loop by design, including approval gates, override capture, uncertainty handling, and clear evidence for agent decisions. Agents recommend and draft; people decide 
  • Close the loop: turn user corrections and overrides into signals that measurably improve the agent 

Evaluation & Reliability 

  • Build evaluation harnesses for multi-step behavior, not single-response accuracy: task completion, tool-call correctness, groundedness, trajectory quality, and regression across model, prompt, and tool changes 
  • Define production metrics for agent quality, reliability, latency, cost, and human intervention rates 
  • Implement guardrails, fallbacks, timeouts, cost ceilings, and end-to-end observability and tracing across agent runs 
  • Design safeguards against prompt injection, unsafe tool use, excessive permissions, data leakage, and other agent-specific security risks 
  • Manage prompt evolution, model drift, and non-determinism while maintaining consistent, measurable system behavior across releases 

Integration & Data 

  • Integrate agents with platform APIs and third-party enterprise systems already running in our customers’ environments 
  • Build retrieval and context pipelines that turn fragmented enterprise data into reliable, permission-aware agent context 
  • Design controlled execution paths for automated actions, with a complete, traceable audit trail 

Platform & Infrastructure 

  • Build and operate backend services on AWS (Lambda, API Gateway, DynamoDB, Step Functions, etc.) 
  • Own significant parts of the system architecture and contribute to key technical decisions 
  • Contribute to infrastructure-as-code and deployment pipelines 

Tech Stack 

  • Languages: TypeScript, Python 
  • Backend: Node.js, Python, AWS Lambda, Step Functions 
  • AI: OpenAI, Anthropic, MCP and related agent/tool protocols, embeddings and vector search 
  • Frontend: React, Next.js, Tailwind CSS 
  • Infrastructure: AWS, Terraform 
  • Testing: Jest, Playwright, pytest 

What We’re Looking For 

Must Have 

  • 6+ years of software engineering experience, including production systems 
  • Strong understanding of LLM behavior, limitations, and failure modes, especially how errors compound across a multi-step run 
  • Experience with LLM APIs, tool and function calling, and designing planning and execution loops 
  • Experience evaluating and debugging non-deterministic systems 
  • Solid backend and cloud experience (AWS or equivalent) 
  • Proficiency in TypeScript and/or Python 

You Should Be Comfortable With 

  • Debugging across distributed and non-deterministic systems 
  • Making explicit tradeoffs between accuracy, latency, reliability, and cost 
  • Working in ambiguous problem spaces where the right architecture isn't obvious yet 
  • Owning production systems end-to-end 
  • Choosing conventional software over AI when AI isn't the right solution 

Nice to Have 

  • C#, Microsoft .NET Framework 
  • Tool and interop protocols such as MCP 
  • Experience building production LLM systems, including tool-using or multi-step agentic workflows beyond simple prompting and chat interfaces 
  • Evaluation pipelines and metrics built specifically for agentic systems 
  • Experience in regulated or domain-heavy systems (validation, audit trails, controlled change) 
  • Retrieval and grounding techniques for supplying agent context 
  • Workflow and durable-execution platforms (Temporal, Step Functions, n8n, etc.) 
  • Containerization and orchestration (ECS, EKS, Kubernetes) 
  • Infrastructure as Code (Terraform or similar) 

STARLIMS is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, creed, religion, color, national or ethnic origin, citizenship, sex, sexual orientation, gender identity and expression, genetic information, veteran status, age or disability status.  

Similar Jobs

46 Minutes Ago
Remote or Hybrid
45K-85K Annually
Junior
45K-85K Annually
Junior
Artificial Intelligence • Fintech • Insurance • Marketing Tech • Software • Analytics
Handles inbound calls and warm leads, consults customers on insurance needs, recommends appropriate Property and Casualty products, and converts prospects into policyholders. The role includes paid licensing and sales training, commission opportunities, customer communication, lead conversion, and flexible remote work. Representatives must work a weekday and weekend schedule, maintain a dedicated home workspace, and meet specified wired internet requirements.
Top Skills: PcWired High-Speed Internet
46 Minutes Ago
Remote or Hybrid
79K-130K Annually
Mid level
79K-130K Annually
Mid level
Automotive • Hardware • Internet of Things • Mobile • Software • App development • PropTech
Analyzes chatbot conversations and interaction data to identify performance issues, trends, anomalies, and root causes. Leads retraining, response optimization, AI workflow testing, QA, and performance measurement. Coordinates cross-functional improvement initiatives, defines AI-ready knowledge standards, reports business impact, and advises customer experience and technical support teams on chatbot quality and best practices.
Top Skills: Artificial IntelligenceChatbotsMS OfficeNatural Language Processing
46 Minutes Ago
Remote
USA
225K-275K Annually
Senior level
225K-275K Annually
Senior level
Artificial Intelligence • Cloud • Information Technology • Energy • Infrastructure as a Service (IaaS)
Leads Riot’s corporate M&A, strategic investments, joint ventures, and development capital structuring for data center infrastructure. Responsibilities include sourcing and executing transactions, building valuation and returns models, managing diligence, negotiating with capital partners and advisors, preparing board and investment committee materials, and supporting post-close integration. The role partners with executive leadership, finance, legal, tax, development, and site acquisition teams.

What you need to know about the Seattle Tech Scene

Home to tech titans like Microsoft and Amazon, Seattle punches far above its weight in innovation. But its surrounding mountains, sprinkled with world-famous hiking trails and climbing routes, make the city a destination for outdoorsy types as well. Established as a logging town before shifting to shipbuilding and logistics, the Emerald City is now known for its contributions to aerospace, software, biotech and cloud computing. And its status as a thriving tech ecosystem is attracting out-of-town companies looking to establish new tech and engineering hubs.

Key Facts About Seattle Tech

  • Number of Tech Workers: 287,000; 13% of overall workforce (2024 CompTIA survey)
  • Major Tech Employers: Amazon, Microsoft, Meta, Google
  • Key Industries: Artificial intelligence, cloud computing, software, biotechnology, game development
  • Funding Landscape: $3.1 billion in venture capital funding in 2024 (Pitchbook)
  • Notable Investors: Madrona, Fuse, Tola, Maveron
  • Research Centers and Universities: University of Washington, Seattle University, Seattle Pacific University, Allen Institute for Brain Science, Bill & Melinda Gates Foundation, Seattle Children’s Research Institute

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account