Chatbot Developer

Founding Engineer (Bangalore)

The problem:

Business enterprises overpay vendors - on every batch of invoices, on every month because the data that would catch lives in different systems. We are building an AI agent that processes invoices end-to-end, reasons across all the relevant sources, flags genuine discrepancies, and acts - without a human having to investigate each one.

What you will own

Everything engineering. Schema design to deployment to the 2am fix when something breaks in production. There is no tech lead above you. There is no platform team. There is the architecture, you, and the founders. Concretely, this means building:

• A multi-stage agentic pipeline that takes a vendor invoice and produces a structured decision - fully autonomous for clear cases, escalating to human review for genuinely ambiguous ones. We use LangGraph, but if you've built equivalent systems with Temporal, Prefect, or custom state machines with LLM orchestration, that works
• An LLM-powered extraction layer that handles real invoices - scanned PDFs, stamped documents, inconsistent layouts - and returns structured output
• A graph data model that connects invoices to various sources and can traverse those relationships to detect discrepancies
• ERP connectors, GST validation logic, and a write-back layer that closes the loop

What we need

• Strong Python. Async FastAPI, clean service boundaries, tests that actually catch bugs. You have shipped Python backends that handled real production load
• Solid Postgres. Complex queries, schema design, migrations without downtime, row-level security for multi-tenant data. pgvector is a plus - if not, you pick it up fast
• LLM API experience in production. You have called an LLM API for something that real users depended on. You know about structured output, retry logic, cost management, prompt versioning. A side project counts if it was genuinely deployed
• Comfort with graph data models. You understand when a graph is the right structure and when it is not. You do not need deep Neo4j production experience - you need to understand graph relationships conceptually and be willing to learn Cypher. It is a 2-day ramp for the right person
• Working knowledge of deployment. Deployed and operated production workloads on GCP. Cloud Run, Cloud SQL, Cloud Storage, Redis — you're comfortable across the stack. If you've done it on AWS, the translation isn't hard, but GCP is where we are
• You own things. Not "I contributed to" - you designed it, shipped it, and fixed it when it broke. That pattern needs to be visible in your history

Good to have, not mandatory

• Built an agentic pipeline with multiple stages
• Any fintech, P2P domain experience - even tangential
• Worked at a startup with under 20 people
• Has a GitHub, blog, or writeup that shows how you think about a hard technical problem

What you get

• The hardest engineering problem you would have worked on. This is not CRUD with an LLM bolted on
• Real ownership. First engineering hire. Your architectural decisions will be in this product five years from now
• Equity that matters. ESOP - Open to discussion. We are pre-seed - this is a bet, not a guarantee. We will not pretend otherwise
• No meetings tax. You work directly with the founders. The product is specified clearly. You know what you are building and why

Honest about stage: We do not have a production ready infra yet. We have a complete architecture specification and a working prototype. If you need the stability of an established engineering org, this is not the right moment. If you want to build something real from zero and own a meaningful piece of it, it is.

The founders

One of us has spent 20 years building revenue and operational engines at companies where there was no playbook - part of the pilot team that established the world's largest search company's direct sales operations in India, managed global operations for a global mobile advertising platform, scaled a B2C platform to become one of India’s leading edtech platforms and most recently worked on building an enterprise Agentic Voice AI platform. The other has spent 15 years taking AI from demo to production in domains where failure is expensive - voice, lending, and conversational systems across a Series D conversational AI company, a major telco, a Big 4, and a leading NBFC.

Two IIT/IIM alumni who have both watched AI work in enterprise, and know exactly what it takes to get it there. We are not building this product because it sounds interesting. We are building it because we have both sat across the table from CFOs who know they are losing margin and have no tool capable of doing anything about it.

UKG is looking to hire a Lead Software Engineer to join our extremely talented Data Science team. As a Lead Software Engineer at UKG, you’ll be embedded on the Data Science team where you can work on the next generation AI Platform. You’ll get to work directly with other Engineers, Software Testers, Business Analysts, Product Managers, and Directors, all of whom make up the team. In this highly collaborative environment, you will have the opportunity to grow as a software engineer, and even help mentor others.

This position requires excellent object-oriented programming skills and knowledge of design patterns. They will be involved in the deployment of our AI Platform/Services solution on the cloud. The job requires you to be able to design, develop, troubleshoot, and debug complex software applications at the enterprise level. We are looking for a software engineer who is passionate about programming and truly enjoys what they do. The ideal candidate for the Python Engineer position is someone who has a can-do attitude and is an innovative thinker.

UKG works in an agile environment where there are daily stand-ups, code reviews, and constant communication within each self-managed cross-functional team. The ability to communicate effectively with Business Analysts and Software Testers, as well as work closely with other team members are key components for success in this position.

Primary Responsibilities:

• Collaborate with members of the team to solve challenging engineering tasks on time and with high quality.
• Engage in code reviews and training of team members.
• Support continuous deployment pipeline code.
• Situationally troubleshoot production issues alongside the support team.
• Continually research and recommend product improvements.
• Create and integrate features for our enterprise software solution using the latest Python technologies.
• Write web services, business objects, and other middle-tier framework using Python
• Actively communicate with team members to clarify requirements and overcome obstacles to meet the team goals.
• Leverage open-source and other technologies and languages outside of the Python platform.
• Develop cutting-edge solutions to maximize the performance, scalability, and distributed processing capabilities of the system.
• Provide troubleshooting and root cause analysis for production issues that are escalated to the engineering team.
• Work with development teams in an agile context as it relates to software development, including Kanban, automated unit testing, test fixtures, and pair programming.

Qualifications

• 5-8 years experience as a Python developer on enterprise projects using Python, Flask, FastAPI, Django, PyTest, Celery and other Python frameworks.
• Software development experience including: object-oriented programming, concurrency programming, modern design patterns, RESTful service implementation, micro-service architecture, test-driven development, and acceptance testing.
• Familiarity with tools used to automate the deployment of an enterprise software solution to the cloud, Terraform, GitHub Actions, Concourse, Ansible, etc.
• Proficiency with Git as a version control system
• Experience with Docker and Kubernetes
• Experience with relational SQL and NoSQL databases, including MongoDB and MSSQL.
• Experience with object-oriented languages: Python, Java, Scala, C#, etc.
• Experience with testing tools such as PyTest, Wiremock, xUnit, mocking frameworks, etc.
• Experience with GCP technologies such as BigQuery, GKE, GCS, DataFlow, Kubeflow, and/or VertexAI
• Excellent problem solving and communication skills.

Job Description:

Candidate must have 2 to 5-years of experience in various phase of development of a python-based application or API development.

Requirements:

Must Have:  Strong expertise in PYTHON and its built-in data structures, developing API using flask or fastapi, data wrangling using standard python frameworks like pandas, NumPy etc., integration of various applications (third party or inhouse) with python.

Good to Have: Deployment using Nginx, GUnicorn, IIS, docker and Kubernetes etc. Good understanding of optimization solutions like differential evolution. Hands on experience with python packages like Scipy.  Tkinter to make python-based applications.

Roles and Responsibilities:

• Understanding/gathering the requirements from stakeholder, formulating the problem, and leveraging AI/ML to solve the business problems.
• Integration of third party or in house application with python solution.
• Working on Deployment and optimization of various engineering problems using Numerical/Constraint optimization frameworks such as Differential Evolution and deploy a web-based API using Flask and Nginx/IIS.
• Unit testing of various python modules developed and testing of the API.