← Back to jobsJob ID col-cmvv4i7vp042q42b9vciizrb9

PlanePosted 30+ days ago

Software Engineer, AI Application

Full-time
Remote
2+ years
Competitive
Posted 30+ days ago

Plane is building an open, adaptable work management platform designed for collaboration between humans and AI agents. The Software Engineer, AI Application will build production agent workflows, MCP servers, retrieval systems, evaluation tooling, and customer-facing agent interfaces using Python, while partnering with engineering and product teams to ship reliable AI capabilities.

Posted
30+ Days Ago
Source
jobs.ashbyhq.com
Sector
Information Technology & AI

Opens the employer's application page in a new tab

Responsibilities

  • Build agent workflows that operate on Plane data, including planning loops, tool calling, multi-step execution, and recovery when a step fails
  • Design and ship MCP servers that expose Plane capabilities as tools, defining the schemas, permissions, and error semantics that make them safe for a model to call
  • Own the retrieval layer end to end, covering chunking strategy, embedding models, vector storage, hybrid search, and reranking
  • Build the agent interfaces that customers actually touch, including streaming output, intermediate step visibility, approval gates, and clean interruption
  • Establish the evaluation harness for everything you ship, defining datasets, regression suites, and the offline and online metrics that decide whether a change goes out
  • Instrument tracing, token cost, and latency across agent runs, and drive down the failure modes that show up in production
  • Design the permission and audit model for agent actions so an agent can only reach what the acting user can reach
  • Evaluate models, frameworks, and techniques as they land, and make a clear recommendation on what Plane should adopt and what it should skip
  • Partner with backend, frontend, and product engineers to take a working prototype to a shipped surface

Qualifications

  • Two or more years building production software, including at least one year shipping features backed by large language models
  • Strong Python and experience operating services in production, including debugging them under real traffic
  • Experience building agent systems that call tools, covering the orchestration, the failure handling, and the loop control that keeps them from running away
  • Working knowledge of retrieval systems, including embedding models, chunking tradeoffs, vector databases, and the retrieval quality problems that follow
  • Experience building an evaluation harness for a non-deterministic system and using it to make a ship or no-ship call
  • Examples of AI features you shipped to real users rather than to demos or notebooks

Preferred

  • You have built or published an MCP server
  • You have run agents against production data with a real permission model behind them
  • You have worked on developer tools, project management, or another product with a complex domain model
  • You have contributed to open source. Plane is open source, and you will see your work in public

Required skills

AI Agent SystemsAI Feature DeploymentEmbedding ModelsMCP Server DevelopmentProduction Software EngineeringPythonRetrieval SystemsVector Databases

Full job description

Plane is building an open, adaptable work management platform designed for collaboration between humans and AI agents. The Software Engineer, AI Application will build production agent workflows, MCP servers, retrieval systems, evaluation tooling, and customer-facing agent interfaces using Python, while partnering with engineering and product teams to ship reliable AI capabilities.

Responsibilities

  • Build agent workflows that operate on Plane data, including planning loops, tool calling, multi-step execution, and recovery when a step fails
  • Design and ship MCP servers that expose Plane capabilities as tools, defining the schemas, permissions, and error semantics that make them safe for a model to call
  • Own the retrieval layer end to end, covering chunking strategy, embedding models, vector storage, hybrid search, and reranking
  • Build the agent interfaces that customers actually touch, including streaming output, intermediate step visibility, approval gates, and clean interruption
  • Establish the evaluation harness for everything you ship, defining datasets, regression suites, and the offline and online metrics that decide whether a change goes out
  • Instrument tracing, token cost, and latency across agent runs, and drive down the failure modes that show up in production
  • Design the permission and audit model for agent actions so an agent can only reach what the acting user can reach
  • Evaluate models, frameworks, and techniques as they land, and make a clear recommendation on what Plane should adopt and what it should skip
  • Partner with backend, frontend, and product engineers to take a working prototype to a shipped surface

Preferred

  • You have built or published an MCP server
  • You have run agents against production data with a real permission model behind them
  • You have worked on developer tools, project management, or another product with a complex domain model
  • You have contributed to open source. Plane is open source, and you will see your work in public
  • MCP server
  • Production data management
  • Developer tools
  • Project management
  • Complex domain model
  • Open source contribution

Company

  • Project management software for teams and AI agents
  • Hyderabad, Telangana, IND
  • https://plane.so/
  • Founded in 2023
  • 51-200 employees

Qualifications

  • Two or more years building production software, including at least one year shipping features backed by large language models
  • Strong Python and experience operating services in production, including debugging them under real traffic
  • Experience building agent systems that call tools, covering the orchestration, the failure handling, and the loop control that keeps them from running away
  • Working knowledge of retrieval systems, including embedding models, chunking tradeoffs, vector databases, and the retrieval quality problems that follow
  • Experience building an evaluation harness for a non-deterministic system and using it to make a ship or no-ship call
  • Examples of AI features you shipped to real users rather than to demos or notebooks
  • You have built or published an MCP server
  • You have run agents against production data with a real permission model behind them
  • You have worked on developer tools, project management, or another product with a complex domain model
  • You have contributed to open source. Plane is open source, and you will see your work in public
  • Two or more years building production software, including at least one year shipping features backed by large language models.

Required skills

  • AI Agent Systems, AI Feature Deployment, Embedding Models, Evaluation Harnesses for Non-Deterministic Systems, Large Language Model (LLM) Feature Development, MCP Server Development, Permission Models for Agent Systems, Production Software Engineering, Python, Retrieval Systems, Tool Calling and Agent Orchestration, Vector Databases

Preferred skills

  • You have built or published an MCP server

Experience

  • 2+ years

Job details

Employment type

Full-time

Seniority level

2+ years

Date posted

Aug 18, 2026

Work mode

Remote

Job source

jobs.ashbyhq.com

Company

Plane

Information Technology & AI

Project management software for teams and AI agents

  • United States
  • Information Technology & AI
  • 51-200 employees
  • Founded 2023
  • plane.so

Similar jobs

Matched on role, skills and location · live jobs only

See more AI Engineer jobs

Landscape Forms

1d ago

New

Senior Software Engineer – AI & Business Applications

Full-timeRemoteUnited StatesCompetitive

Landscape Forms is hiring a Senior Software Engineer to develop software and AI-powered solutions that improve how teams work across the company.

Why similarSame rolePython

Indigo Slate

1d ago

New

AI-Native Software Engineer

Full-timeRemoteUnited StatesCompetitive

Zensar Technologies is seeking a full-stack, AI-native software engineer to build capabilities that secure current products and AI-built, agent-operated systems.

Why similarSame rolePython

SPECTRAFORCE

1d ago

New

AI Engineer/Architect

Full-timeRemoteUnited StatesCompetitive

SPECTRAFORCE is seeking an AI Engineer/Architect for a seven-month remote role. The role focuses on developing AI models and implementing AI-based NLP and APIs, as well as integrating and deploying AI models with UI platforms.

Why similarSame rolePython

Get new AI Engineer jobs by email

Create job alert

Software Engineer, AI Application

Plane · Competitive

Apply on company site