Senior Software Engineer, AI Agents & Evals at Terrabase · Remote only · 3 - 15 years · ₹20L - ₹50L / yr · Bootstrapped · Remote only · Posted 23 Jun 2026
PythonExperience: 5+ years production software engineering, with 2+ years working directly on LLM or agent systems in production.
Location: Remote
To streamline and fast-track screening, please submit your details here (if you haven’t already): https://airtable.com/appbtkr4odapnb5I6/pagqo91lKv3VJg3GT/form
We’ll review your responses as part of the initial screening process. Please make sure you complete and submit all details through the form to be considered for the next stage. Submissions outside the form may not be considered.
Why This Role Matters
Terrabase builds agent infrastructure that enterprise customers rely on daily for SQL generation, forecasting, data analysis, and artifact delivery. Our orchestration layer routes between specialized sub-agents, manages typed handoff contracts, runs structured eval suites, and enforces correctness across every turn.
This is not a research-prototype role. You will build and evolve agent architecture, but always in service of making the system observable, typed, evaluated, recoverable, and boringly reliable in production.
What You Will Do
Own the harness architecture and middleware stack. Our LangGraph orchestrator routes between sub-agents through a layered middleware stack: file upload handling, source resolution, local context, workspace sync, state hydration, aggregation barriers, and typed handoff contracts. You will extend this stack, enforce its contracts in code, and keep it operational as routing logic and agent surfaces evolve.
Maintain typed contracts and boundaries. Agent handoffs at Terrabase carry typed contracts with barrier conditions and retry predicates. You will design these contracts, enforce them with strict typing, manage backward compatibility when contracts change, and write the contract tests that prevent silent regressions.
Own the eval suites. We run structured eval suites across routing decisions, context-resolution accuracy, multi-turn coherence, visual reference alignment, and artifact correctness. You will extend coverage, write new evals where gaps exist, and build CI gates that block releases when regressions are detected. A routing change or prompt change with no eval coverage does not ship.
Triage production failures and close the loop. When an agent turn fails in production, you will trace it in LangSmith, identify the failure class, and convert it into a durable regression test. You will own the release gates, keep prompts and runtime contracts in sync, manage feature flag rollout risk, and remove dead paths as the system evolves.
Own SQL and artifact correctness. Our agents generate SQL over customer schemas and produce structured artifacts (reports, dashboards, data sheets) under a strict schema contract. You will own the correctness layer: source grounding, schema-aware validation, provenance surfaces, and the eval infrastructure that catches generated artifact failures before they reach customers.
Build and maintain HITL workflows. Human-in-the-loop checkpoints let users intervene, redirect, or approve mid-chain. You will design these workflows, enforce their resumable state contracts, and ensure they degrade gracefully when interrupted.
Instrument for traceability. You will extend LangSmith tracing coverage, add structured span annotations, and build the tooling that lets us diagnose a bad agent turn from production trace data alone, without requiring a local reproduction.
What We Are Looking For
- 5+ years production software engineering, with strong Python fundamentals
- 2+ years working hands-on with LLM-based systems: agent loops, tool use, context management, or inference pipelines
- Experience with LangGraph, LangChain, OpenAI/Anthropic tool-use systems, or equivalent multi-step agent/runtime orchestration
- Practical eval engineering: you have built or extended eval harnesses, written automated test cases for agent behavior, and treated evaluation as an ongoing engineering discipline
- Strong engineering hygiene: strict typing, small interfaces, contract tests, clear schema migrations, and CI discipline
- Ability to debug from production traces and artifacts, not only local reproductions
- Comfort working across prompts, Python runtime code, TypeScript product surfaces, data systems, and eval infrastructure
- Systems thinking: you design for observability, recovery, and state management, not just the happy path
- Maintenance ownership mindset: you triage, close loops, and leave systems more debuggable than you found them
- Pragmatic judgment: you can distinguish between reliability-critical infrastructure and speculative abstraction
Bonus Points
- HITL workflow design: checkpoints, approvals, mid-chain interrupts, resumable state
- Context engineering depth: chunking strategies, retrieval-augmented generation, semantic routing, re-ranking
- Experience with LangSmith, Weights and Biases, or similar trace and evaluation platforms
- Prior work shipping agent systems to enterprise customers where SQL or data correctness is a hard requirement
- Experience with mypy, Pydantic contracts, or strict typing disciplines in a production Python codebase
Life at Terrabase
We are a sharp, focused, fully remote team building agent infrastructure that enterprise customers trust with their data. You will work directly alongside the engineer who designed this harness, with broad ownership, generous compute budgets, and a culture that treats reliability as a product requirement, not a research topic.
Terrabase is an equal-opportunity employer. We celebrate diversity and are committed to building an inclusive environment for every team member.
Shubham Vishwakarma
Full Stack Developer - Averlon
About Terrabase
About
Company social profiles
Similar jobs (10)
JavaPython
NodeJS (Node.js)
Go Programming (Golang)Location: Pune/Bengaluru
As a Senior Software Engineer, you will tackle a highly challenging role within our Cyber Security Engineering integration development team. You will be responsible for the End-to-End (E2E) delivery of projects from gathering customer requirements to deploying high-performance data exchange solutions on-prem or in the cloud. We are looking for a Systems-Level Thinker who can seamlessly transition between building complex integrations and architecting high-throughput, low-latency backends. Because each integration may require a different technical approach, we value engineers who love reskilling, following agile best practices, and maintaining an evolving mindset.
Core Responsibilities
Technical Leadership and Architecture
● Systems Engineering: Design, build, and optimize high-throughput, low-latency backend systems and data-exchange layers.
● Architecture and Integration: Participate in planning, defining, and exploring solution alternatives. Architect and estimate deep technical custom solutions and integrations across diverse enterprise tech stacks. ● Stream Processing: Implement event-driven architectures, manage backpressure, and handle real-time state management across security platforms.
● Delivery Ownership: Own projects end-to-end, defining and implementing enablers to evolve solution intent directly alongside our Agile teams.
Team Leadership and Quality
● Mentorship: Actively lead, coach, and mentor junior developers, providing technical guidance to foster professional development.
● Engineering Excellence: Oversee code reviews, build robust CI/CD pipelines, enforce strict quality checks, and ensure rigorous adherence to coding standards.
● Agile Execution: Actively participate in Agile development, including writing, breaking down, and estimating User Stories.
Customer and Stakeholder Collaboration
● Customer Delight: Maintain a strong customer-first attitude while designing, building, and deploying products.
● Technical Communication: Articulate complex technical trade-offs clearly to both business stakeholders and engineering teams.
● Pipeline Management: Manage customer relationships effectively to ensure a continuous flow of project scope, maintaining clear team backlogs.
Job Requirements
● Experience: 5+ years of proven software engineering experience, with a track record of leading small engineering teams or mentoring junior devs.
● High-Throughput Backend Focus: 5+ years of experience engineering robust, real-time backends specifically using Go (Golang) or Java.
● Polyglot and Integration Capability: Deep expertise in at least one or two additional languages/frameworks from our ecosystem: Python, TypeScript, Node.js, React.js, Angular, C#, or C++.
● Computer Science Fundamentals: Excellent knowledge of complex Data Structures, algorithms, and their correct situational usage.
● Adaptability: A passionate programmer who is genuinely open and excited to learn new software development skills as required by changing project demands.
Bonus / Added Advantages
● AI & Intelligent Automation: Hands-on knowledge of AI concepts, Large Language Models (LLMs), and experience building or integrating AI agents to automate complex workflows or security processes.
● Cybersecurity Domain: Experience in the cybersecurity space (SIEM, SOAR, or platform security).
● Modern Web Tech: Strong experience in developing software using modern web technologies.
● E2E Lifecycle: Proven background handling a project completely from discovery to cloud/on-prem deployment.
● Open Source: Active contributions to the Open Source community. (Please share your GitHub/GitLab links in your application!)
PythonRole: Sr. Azure Data Engineer
Experience: 8–10 Years
Work Timings: 1:30 PM – 10:30 PM IST
Location: Bellandur Bengaluru (Work from Office)
Company: Chevron
Employment Type: 6- 12 months Contract
Role Overview
We are seeking an experienced Senior Data Engineer to design and deliver scalable cloud data solutions on Azure. The ideal candidate will have strong expertise in Databricks, PySpark, and modern data architectures, with exposure to energy domain standards like OSDU.
Key Responsibilities
- Architect and design robust Azure-based data solutions using Databricks, ADLS, and PaaS services
- Define and implement scalable data Lakehouse architectures aligned with OSDU standards
- Build and manage end-to-end data pipelines for batch and real-time processing using PySpark
- Establish data governance frameworks including metadata, lineage, security, and access control
- Implement DevOps best practices (CI/CD, Azure Pipelines, GitHub, automated deployments)
- Collaborate with stakeholders to translate business needs into technical solutions
- Develop and maintain architecture documentation, solution patterns, and standards
- Provide technical leadership and mentorship to engineering teams
- Optimize solutions for performance, cost, reliability, and security
- Ensure alignment with enterprise architecture and compliance standards
- Drive adoption of modular and reusable cloud data components
Required Skills & Qualifications
Core Technical Skills
- Azure Databricks, Apache Spark (PySpark), Delta Lake, Unity Catalog
- Azure Data Lake Storage (ADLS), Azure Data Factory, Synapse Analytics
- Strong experience in Python-based data engineering
- Data pipeline development (batch + real-time)
Architecture & Advanced Skills
- Data Lakehouse architecture and distributed systems
- Microservices, APIs, and integration frameworks
- OSDU (Open Subsurface Data Universe) or similar energy data models
DevOps & Tools
- CI/CD tools: Azure Pipelines, GitHub Actions
- Infrastructure as Code: Terraform or similar
Other Skills
- Data governance, security, compliance, and cost optimization
- Strong analytical and problem-solving skills
- Excellent communication and stakeholder management
Python
KubernetesJava
Amazon Web Services (AWS)Mandatory Criteria :
- Candidate must have Strong hands-on experience with Kubernetes of atleast 2 years in production environments.
- Candidate should have Expertise in at least one public cloud platform [GCP (Preferred), AWS, Azure, or OCI).
- Proficient in backend programming with Python, Java, or Kotlin (at least one is required).
- Candidate should have strong Backend experience.
- Hands-on experience with BigQuery or Snowflake for data analytics and integration.
About the Role
We are looking for a highly skilled and motivated Cloud Backend Engineer with 4–7 years of experience, who has worked extensively on at least one major cloud platform (GCP, AWS, Azure, or OCI). Experience with multiple cloud providers is a strong plus. As a Senior Development Engineer, you will play a key role in designing, building, and scaling backend services and infrastructure on cloud-native platforms.
# Experience with Kubernetes is mandatory.
Key Responsibilities
- Design and develop scalable, reliable backend services and cloud-native applications.
- Build and manage RESTful APIs, microservices, and asynchronous data processing systems.
- Deploy and operate workloads on Kubernetes with best practices in availability, monitoring, and cost-efficiency.
- Implement and manage CI/CD pipelines and infrastructure automation.
- Collaborate with frontend, DevOps, and product teams in an agile environment.
- Ensure high code quality through testing, reviews, and documentation.
Required Skills
- Strong hands-on experience with Kubernetes of atleast 2 years in production environments (mandatory).
- Expertise in at least one public cloud platform [GCP (Preferred), AWS, Azure, or OCI].
- Proficient in backend programming with Python, Java, or Kotlin (at least one is required).
- Solid understanding of distributed systems, microservices, and cloud-native architecture.
- Experience with containerization using Docker and Kubernetes-native deployment workflows.
- Working knowledge of SQL and relational databases.
Preferred Qualifications
- Experience working across multiple cloud platforms.
- Familiarity with infrastructure-as-code tools like Terraform or CloudFormation.
- Exposure to monitoring, logging, and observability stacks (e.g., Prometheus, Grafana, Cloud Monitoring).
- Hands-on experience with BigQuery or Snowflake for data analytics and integration.
Nice to Have
- Knowledge of NoSQL databases or event-driven/message-based architectures.
- Experience with serverless services, managed data pipelines, or data lake platforms.
Python
Django
FlaskTitle: Senior Python Developer
Location:- Ahmedabad (Currently work from home)
Salary Range: upto 7.5lpa
Experience Range: 3+ years
Qualification: B.Sc. / B.Tech (CS / IT), MCA, BCA
Responsibility:
- You will work on large data sets
- You will provide data visualization for the platform
- Writes and executes complete testing plans, protocols, and documentation for assigned portion of application; identifies and debugs, and creates solutions for issues with code and integration into application architecture.
- Designs enhancements, updates, and programming changes for portions and subsystems of end-user applications software running on local, networked, and Internet- based platforms.
- Collaborates and communicates with management, internal, and outsourced development partners regarding software applications design status, project progress, and issue resolution.
Functional Knowledge:
- Expert in Python, Machine learning with knowledge of at least one Python web framework Flask, Django etc.
- Expert in server programming, you should be able to implement complex business logic
- Good understanding of the threading limitations of Python, and multi-process architecture
- Good understanding of fundamental design principles behind a scalable application
- Knowledge of event-driven programming in Python
- Strong unit test and debugging skills
- Knowledge of AWS cloud and python Boto lib
- Knowledge of mongo-db
- Proficient understanding of code versioning tools Like Git
- Good understanding of Linux OS
- Knowledge on nltk, scikit, numpy would be an advantage
Compensation and Benefits:
- Excellent Salary Structure
- Employee friendly corporate work culture
- Exposure to interact with US people
- Flexible timings with Saturday and Sunday Off
- Lucrative Rewards and Recognition
PythonDjango
React.jsFlaskJob Type: Full Time
Location: Permanent Remote / Bangalore / Thane
Skills: PYTHON, Django, Reactjs, Vue, Flask
Job Description
Are you passionate enough to be a crucial part of a highly analytical and scalable user engagement platform?
Are you ready learn new technologies and willing to step out of your comfort zone to explore and learn new skills?
If so, this is an opportunity for you to join a high-functioning team and make your mark on our organization!
The Impact you will create in the Job:
- Build campaign generation services which can send app notifications at a speed of 10 million a minute.
- Leverage the power of Kubernetes to maintain clusters running inside VPC's across the world.
- Dashboards to show Real time key performance indicators to clients.
- Develop complex user segmentation engines which creates segments on Terabytes of data within few seconds.
- Use AWS products extensively across our services such as Kinesis Data Streams, Lambda, SQS etc. that form an integral part of our scalable and robust infrastructure.
- As an individual contributor, you will tackle some of our broadest technical challenges that requires deep technical knowledge, hands-on software development, technical leadership, and seamless collaboration with all functions.
- You will envision and develop features that are highly reliable and fault tolerant to deliver a superior customer experience.
- You will get an opportunity to work with some of the best talent in the country while learning from various highly-functional teams in the company.
- Plan and execute the roadmap with the engineering team to build and deliver next-generation systems.
- You will also collaborate with cross-functional teams to meet deliverables throughout the software development lifecycle.
- Identify and improvise areas of improvement through data insights and research.
What we look for?
- 4-7 years’ experience in full stack Python development
- Very strong analytic and problem-solving skills
- Solid understanding of a relevant and globally supported framework- both front-end and back-end, if necessary, for example - Angular, React, Vue, or Django/Flask.
- Solid understanding of engineering best practices, continuous integration, and incremental delivery.
- Proven experience on design and implementation of the overall web and database architecture and updated knowledge on the latest practices and associated versions.
- Ensuring the entire stack is designed and built for speed and scalability.
- Familiarity with RESTful API design.
- Knowledge of continuous integration and deployment.
- Familiarity with Server management and deployment on AWS/GCE.
- Sound knowledge of CSS pre-processors, bundlers, and associated languages/syntaxes/libraries like Sass, Less, and webpack
- Experience implementing testing platforms and unit tests.
What’s in it for you?
- Immense growth, continuous learning and deliver the best to the top-notch brands
- Work with some of the most innovative brains
- Opportunity to explore your entrepreneurial mind-set
- Open culture where your creative bug gets activated.
If this sounds like a company you would like to be a part of, and a role you would thrive in, please don’t hold back from applying! We need your unique perspective for our continued innovation and success!
So let’s converse! Our inquisitive nature is all keen to know more about you.
PythonDjangoJavaNodeJS (Node.js)Amazon Web Services (AWS)Biddano is seeking for an analytical, result driven, multi-skilled candidate for design for the position of Backend Developer. He/She will be responsible for programming languages and tools to analyze current codes and industry developments, formulate more efficient processes, solve problems and create a more seamless experience for users.
The ideal candidate will have strong personal accountability for results, strong commitment to teamwork in support of the company's success, adherence to ethical business practices, and comfort operating in a start-up environment with an ability to prioritize and drive actions to closure.
a start-up environment with an ability to prioritize and drive actions to closure.
Backend Developer
Responsibilities:
- Participate in the entire application lifecycle, focusing on coding and debugging
- Write clean code to develop functional REST APIs Using Django/Python or NodeJs
- Troubleshoot and debug applications
- Perform unit test cases to optimize performance
- Manage cutting-edge technologies to improve legacy applications
- Collaborate with Front-end developers to integrate user-facing elements with server side logic
- Gather and address technical and design requirements
- Provide training and support to internal teams
- Build reusable code and libraries for future use
- Liaise with developers, designers and system administrators to identify new features
- Follow emerging technologies
Skills Required:
- Proven work experience as a Back-end developer
- In-depth understanding of the entire web development process (design, development and deployment)
- Hands on experience with programming languages like Python (Required), typescript(Required), Java.
- Working knowledge of CMS framework
- Familiarity with back-end languages (e.g. HTML, JavaScript and CSS)
- Excellent analytical and time management skills
- Backend:
- Django/DjangoREST, Python (Prefered) or NodeJs.
- Good experience of microservices.
- Hosting and Deployment Solutions:
- Good understanding of AWS which includes(All required):
- Good expertise in Linux.
- EC2 instance management.
- Scalability (Horizontal or Vertical) which includes autoscaling.
- Proper use of S3 for static file management.
- SNS or AWS email service.
- AWS resource cost optimization.
- Proper knowledge of Load Balancers.
- Teamwork skills with a problem-solving attitude
Experience :
- Minimum 4-7 years of experience as a Backend Developer
- B.tech Computer Science, Engineering or similar relevant field
PythonDjango
Ruby on Rails (ROR)NodeJS (Node.js)
JavaPython
JavascriptAmazon Web Services (AWS)
NodeJS (Node.js)PythonJavascriptJavascript
PHPPythonRuby on Rails (ROR)NodeJS (Node.js)
Follow CutshortShubham Vishwakarma
Full Stack Developer - Averlon