For companies:
For professionals:
For everyone:
Responsibilities
Join Planera to build Manny, our AI scheduling assistant, and shape how construction schedulers work with AI on a modern Critical Path Method platform. You will own agent features end to end: designing and evolving the LangGraph/LangChain agent, engineering prompts and tools, integrating LLMs across providers, and holding response quality to a high bar with a real evaluation and observability stack. This is a hands-on applied AI role with a strong software engineering foundation and a focus on reliability, behavior quality, and user impact. You will work directly with the CTO and the lead AI engineer.Key ResponsibilitiesDesign, build, and own Manny features end to end across the agent backend, tools, and UIImprove agent behavior, reliability, and answer quality through prompt engineering, tool design, and changes to the agent control flowEvolve the agent architecture: ReAct loop, routing and controller logic, multi-node graphs, tool selection, and streaming responsesIntegrate and tune LLMs across providers (Anthropic, OpenAI, Google), balancing quality, latency, and cost, including prompt caching and model selectionDesign and extend Manny's tool surface through the MCP server that connects the agent to Planera's scheduling servicesBuild and own the evaluation loop: golden datasets, automated evaluators, snapshot-based replay, and offline and online quality metricsImplement observability for agent runs with tracing, metrics, and structured logging, and use it to debug and improve behavior in productionEnsure safe, sandboxed execution of model-generated code and safe handling of tool side effects and mutationsCollaborate with product, backend, and frontend to deliver AI features end to endRequirements4+ years of software engineering experience, including recent hands-on work building production LLM features.Strong proficiency in Python building production servicesHands-on experience building agentic systems with LLMs: tool and function calling, ReAct or similar loops, and orchestration frameworks such as LangChain/LangGraphPractical prompt engineering skill: shaping model behavior reliably, debugging failures from traces, and managing large prompts and token costExperience evaluating LLM systems: building datasets, writing evaluators, catching regressions, and using tracing and observability toolingExperience with the Model Context Protocol (MCP) or building tool and function-calling integrations for LLMsSolid understanding of API design (REST, websockets, SSE and streaming) and interservice communicationProduct mindset with a focus on user impact and pragmatic tradeoffsExcellent remote communication skillsPreferredExperience with MongoDB and RedisCloud experience (AWS or GCP), containers, and CI/CDGo experience, as most of our backend systems are written in Go, including the MCP tool serverPractical experience with retrieval and augmentation (RAG), embeddings, and vector storesFamiliarity with LangSmith or comparable LLM evaluation and tracing platformsFrontend or React familiarity for agent UI workDomain knowledge in construction tech, project management, or schedulingTech StackPython (Flask), Go, LangGraph/LangChain, LangSmith, MongoDB, Redis, S3, REST/websockets/SSE, Docker, AWS/GCP, Terraform, GitLab CI/CDWhy Join UsImpact: Be at the forefront of transforming a $12.1 trillion industry. Build the AI that changes how the world plans and schedules construction.Culture: Join a smart, spirited team dedicated to innovation and excellence.Growth: Opportunity for professional growth and career advancement in a fast-paced start-up environment.BenefitsCompetitive salary, stock options, benefits package, and a dynamic work environment.
Closes in:
0
days
0
hours
0
min
0
sec
tune NOT FOR YOU? IMPROVE YOUR RESULTS