Full Stack Software Engineer, India

Doxel
Bengaluru +1 more
Hybrid

Who this role is best for

Aimed at mid-to-senior Full-Stack Engineers who have experience building LLM agents and are comfortable with both Python and TypeScript, working in collaboration with analysts and cross-functional teams in Bengaluru.

Best fit for

  • Candidates with production experience in Python and TypeScript and a background in LLM agent development
    — “4+ years of professional software engineering in TypeScript and Python, with systems you owned in production.”
  • Individuals who can design and implement evaluation systems for AI models used by real users
    — “You have measured LLM output quality against ground truth and used the results to decide what to ship.”
  • Engineers who can build full-stack applications with APIs, data pipelines, and web tools
    — “comfortable building full-stack applications end to end: APIs, data pipelines and web apps.”

Things to consider

  • The role demands a high level of collaboration with analysts, BIM, and 3D teams for end-to-end delivery.
    — “Work across teams: partner with analysts, Product, and the BIM, data and 3D teams to define requirements and deliver end to end.”

How to stand out

  • Highlight experience in building LLM agents with real-world user impact and validation processes.
    — “build evaluation into the system: offline evaluation sets from human-reviewed projects, precision and recall by trade, and regression checks before every rollout.”
  • Showcase your ability to design and implement full-stack systems in Python and TypeScript.
    — “full-stack job management and training tools in Python and TypeScript for our mapping operations team.”
  • Emphasize your hands-on experience with prompt design, context creation, and structured outputs for LLMs.
    — “hands-on experience building LLM agents or LLM-backed applications used by real users: tool calling, structured outputs, prompt and context design.”
  • Demonstrate your understanding of backend systems, including async programming and SQL modeling.
    — “Solid backend fundamentals: async and concurrent programming, SQL and relational data modeling, and designing for retries, idempotency and cost.”
  • Include experience with cloud platforms and workflow orchestration tools like Airflow.
    — “Experience with cloud platforms (GCP preferred), containers, CI/CD, and workflow orchestration such as Airflow.”
Pace · Fast PacedCollaboration · HighAutonomy · HighDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • Own the agent harness: design the tools, context and guardrails an LLM agent uses to map schedule activities to building elements
  • Build evaluation into the system: offline evaluation sets from human-reviewed projects, precision and recall by trade, and regression checks before every rollout
Typical background
4+ years of professional software engineering in TypeScript and Python

Skills & requirements

Required

PythonTypeScriptComputer_visionAISoftware_development

Preferred

Project_managementTeam_leadership

Stack & domain

PythonTypeScriptReactLLMComputer VisionAIMentoringCollaborationConstructionSoftware Engineering

About the role

Original posting from Doxel via Lever

Construction is the second-largest industry in the world—nearly 4x the size of SaaS—yet it still operates without the automated feedback loops that modern software teams rely on. Without real-time observability, issues are detected too late, contributing to over $3 Trillion in annual global waste.

Doxel brings computer vision and AI to construction, giving teams real-time visibility into progress, risk, and execution. From hospitals to data centers, and from field leaders to executive teams, Doxel is used every day to support better decisions and faster delivery. Our platform is trusted by industry leaders including Shell, Genentech, HCA Healthcare, Kaiser, Turner, and Layton.

Doxel’s automated progress tracking solution keeps teams aligned with hard facts that leave no ambiguity on where the project is today, where it will be tomorrow and what decisions need to be made to land it on schedule and on budget. This enables our customers to deliver projects, on average, 11% ahead of schedule with up to 16% savings on monthly cash flow.

Backed by Insight Partners and Andreessen Horowitz and with a rapidly growing team of engineers, scientists, construction veterans, and Enterprise go-to-market teams, we're driven to help our customers win. 

Join us as we continue our journey to transform the $15T Construction Industry!

The Role

As a Full-Stack Engineer on our Schedule Mapping team, you will own the agentic system that connects a customer's construction schedule to their 3D building model. That mapping is what lets Doxel tell a general contractor whether a project is ahead of or behind plan, element by element.

Today an LLM produces a first pass and a team of analysts reviews it. Your job is to make the agent accurate enough that analysts move from correcting to validating, across hundreds of active projects.You will build the agent harness (tools, skills, guardrails and evaluation) in Python, and full-stack job management and training tools in TypeScript and Python for our mapping operations team.

You will work closely with our analysts, Product, and the data and 3D teams, and you will mentor other engineers on the team.If you want to put LLM agents into production where accuracy is measured every day by expert reviewers, this is the role for you.

What You'll Do:

  • Own the agent harness: design the tools, context and guardrails an LLM agent uses to map schedule activities to building elements, and ship changes to production safely.
  • Build evaluation into the system: offline evaluation sets from human-reviewed projects, precision and recall by trade, and regression checks before every rollout.
  • Control cost and reliability: budgets per run, caching for incremental schedule and model updates, retries, and tracing that explains every pick.
  • Close the feedback loop: turn analyst corrections into better context, rules and tools, so accuracy improves with every reviewed project.
  • Build operations tooling: job management that moves mapping work out of ticket trackers, review workflows, and training tools for new analysts, in Python and TypeScript.
  • Work across teams: partner with analysts, Product, and the BIM, data and 3D teams to define requirements and deliver end to end.
  • Lead and mentor: write design docs, review code, and raise the engineering bar for the team in India.

Who You Are & What You'll Bring:

  • 4+ years of professional software engineering in TypeScript and Python, with systems you owned in production.
  • Hands-on experience building LLM agents or LLM-backed applications used by real users: tool calling, structured outputs, prompt and context design.
  • An evaluation mindset: you have measured LLM output quality against ground truth and used the results to decide what to ship.
  • Full-stack range: you are fluent in both TypeScript and Python and comfortable building full-stack applications end to end: APIs, data pipelines and web apps. Deep React experience isn't required.
  • Solid backend fundamentals: async and concurrent programming, SQL and relational data modeling, and designing for retries, idempotency and cost.
  • Experience with cloud platforms (GCP preferred), containers, CI/CD, and workflow orchestration such as Airflow.
  • You use AI coding tools every day and know where they help and where they don't.
  • Clear communication with non-engineers, and a habit of owning outcomes, not only tasks.

Preferred:

  • Experience designing agent harnesses or multi-agent systems, with any framework or none: Anthropic or OpenAI SDKs directly, LangGraph, LangChain or similar.
  • Retrieval and search (RAG, BM25, embeddings) over structured data.
  • React experience, and experience building human-in-the-loop review or annotation systems.
  • Familiarity with construction, BIM, 3D data, or scheduling tools such as Primavera P6 or Microsoft Project.

Doxel is an equal opportunity employer and actively seeks diversity at our company. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status.

Source: Doxel careers (Lever)

Similar roles