
Experience: 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.

About Terrabase
About
Similar jobs (10)
Responsibilities:
• Help define and create Backend architecture and deployment using Python- Django-AWS in an agile environment with lots of ownership and active mentoring
• Work with the Product and Design teams to build new features to solve business problems and fill business needs
• Participate in code reviews to create robust and maintainable code
• Work in an agile environment where quick iterations and good feedback are a way of life
• Interact with other stakeholders for requirement, design discussions and for adoption of new features • Communicate and coordinate with our support and professional services teams to solve customer issues
• Help scale our platform as we expand our product across various markets and verticals globally
As a young, fresh startup, we are hoping to be joined by self-starting, hardworking, passionate individuals who are committed to delivering their best, who can grow into future leaders of FactWise.
Primary Skills: Database Systems (SQL), Python Flask/Fast API/Django frameworks specifically
Requirements:
- Highly proficient in fundamentals of Python web development frameworks like Flask, Django and Fast API
- Demonstrated experience in developing APIs using Python frameworks
- Should have deep knowledge in PostgreSQL, MS SQL Server and other SQL based Databases
Kunato.AI is a NY-based IT firm helping to create the first marketplace that monetizes digital content on the internet (i-commerce). We have patented our technology - a quantitative deep tech system that predicts, assigns, and updates the value of any digital content in real time without the need for human intervention. Our system has the potential to create a new digital goods marketplace that will revolutionize the way we consume, create and search for content on the Internet.
We are looking for a Rust Developer (with 2-6years of experience) to join our cutting-edge development team as it grows. The candidate must be comfortable working in an agile environment and has the ability to take the lead when necessary.
Roles and Responsibilities:
- Responsible for developing the product as per the product specification defined by the product managers
- Responsible for preforming research on the best methods of implementing the requirements
- Author and curate technical documentation to support delivery, maintenance, and adoption
- Work with programmers, engineers, and management heads to identify process improvement opportunities, propose system modifications, and devise governance strategies to optimize the overall performance
- Design and develop automated deployment and maintenance mechanisms
- Solving development challenges and making architectural decisions by understanding the larger picture of the projects goals
- Expanding your existing skill-set, and picking up on various rust dependent frameworks
- Confidently communicating and collaborating with your fellow developers in a remote team environment
Essential skills:
- Must have experience in Rust programming language
- Have excellent knowledge of different data structures and algorithms
- Working knowledge of any other programming language Python, Java, or JavaScript is good to have
- Experience with, or understanding of, Kafka or Redis, Cloud infrastructure services, Docker is an added advantage
- Experience with SQL or NoSQL databases, MySQL, MongoDB, Elasticsearch, etc.
- Experience in Backend and APIs development
- Experience in analysing and optimizing the platform’s performance
- Excellent verbal communication skills
Your responsibilities as a backend engineer will include:
- Back-end software development
- Software engineering and designing data models and write effective APIs
- Working together with engineers and product teams
- Understanding business use cases and requirements for different internal teams
- Maintenance of existing projects and New feature development
- Consume and integrate classifier/ ML snippets from Data science team
What we are looking for:
- 2+ years of industry experience with the Python and Django framework.
- Degree in Computer Science or related field
- Good analytical skills with strong fundamentals of data structures and algorithms
- Experience building backend services with hands-on experience through all stages of Agile software development life cycle.
- Ability to write optimized codes,debug programs, and integrate applications with third party tools by developing various APIs
- Experience with Databases.
- Experience with writing REST-APIs.
- Prototyping initial collection and leveraging existing tools and/or creating new tools
- Experience working different types of datasets (e.g. unstructured, semi-structured, with missing information)
- Ability to think critically and creatively in a dynamic environment, while picking up new tools and domain knowledge along the way
- A positive attitude, and a growth mindset
Bonus:
- Experience with relevant Python libraries such as Requests, sklearn, Selenium
- Hands on experience in Machine learning implementations
- Experience with Cloud infrastructure (e.g. AWS) and relevant microservices
- Good Humor
Note- We are currently working from home due to the pandemic. If selected you may work from a remote location though once office reopens candidate must work from Office.
Who We are
At e6data (https://e6x.io/">https://e6data.io) we’re building core algorithms that makes querying 25 - 200X more performant (i.e. faster and/or cheaper) than every other analytics platform in the world. This results in billions of dollars of value unlocked across faster analytics, savings on compute / infra, and new use cases becoming possible.
Our core team has 100+ years of combined experience and 10+ patents across diverse but complementary disciplines like real time databases, time series databases, SQL OLAP engines, distributed computing platforms, stream processing, and log analytics. Two of the founding team are second time founders with past exits.
We are passionate about solving the deepest and most important problems in computer science, and believe in making our technology available to customers regardless of their location, size, or budget. Our vision is for e6data to power every analytical workload in the world - regardless of deployment scenario (cloud, on-premise, edge), across every use case (end user queries, ETL / data pipelines), and every latency requirement (batch, streaming / real time).
What you'll do?
- Write awesome code
- The focus will be on performance of our data platform
- Identify tactical and long-term product improvements (could be code, script, etc.)
- Responsible for Planning and executing Metadata and Governance tool supports
- Build our internal Data Platform using exdata
- Adding scalable functionality to the system for new features like UDF's, sql functions etc
What are we looking for?
- Worked with Python for a minimum of 2 years
- Well versed with Django REST framework
- Knowledge of document based data stores like MongoDB
- Strong team player
- A passion for continuous learning and growth (both at a personal and team level)
- Experience (or enjoys) working in a startup will be an added advantage
Type: Individual contributor with good hands on proficiency.
Must have
- Strong proficiency in at least one of Java, Ruby, Python
- Exposure to databases: any of PostgreSQL, MySQL, Apache Cassandra
- Any NoSQL database experience is a plus
- Exposure to AWS cloud infrastructure: EC2 or S3
- Proficiency with Git
- MUST: Using REST to make API calls.
Great to have:
- Experience working with one or more middleware, enterprise bus, queueing frameworks
- Any of Memcached/Redis, Apache Kafka / RabbitMQ / PubSub+ / AmazonMQ
Soft skills:
- Appreciation for clean and well documented code
What will you do at Tradyl:
(Examples for illustration only)
- Build a shipping service module that is called by our website to query shipping rates from India to a destination country. Configure this to so that an Ops person can update shipping costs as and when they change. Own deployment and monitoring of this service.
- Use Zapier to build a workflow to export a MixPanel report into a Google sheet every day.
- Change our supplier portal (built on bubble.io) to make an API call to our customer facing site, whenever a supplier modifies his profile.
- Write an alert mechanism that identifies catalogues with insufficient information and makes them non discoverable, which can run every day.
- Work with Business Team to design a workflow for product inwarding using Airtable. Write a small app within Airtable so that whenever a product is updated as “shipped” in airtable, it updates the customer facing website.
- Use an open source dashboarding framework to create a quick dashboard to track important business events.
Job Description
Viaan Industries Limited is looking for a Software Developer who is motivated to combine the art of design with the art of programming.The ideal candidate for this position will have a broad technical skill set and extensive experience in this industry. As a result, the candidate should be able to design, develop, test and deploy the products required for the company's needs. Moreover, the candidate should be able to work with other developers in determining product strategy.
Responsibilities
- Own the product : Design, Develop & Deploy
- Ensure Quality & sustainability of the architecture
- Obsess about code quality, automated testing, continuous integration, code reviews, and documentation
- Provide quick & creative solutions for day-to-day operational issues
- Assure that all user input is validated before submitting to back-end.
- Ensure the technical feasibility of UI/UX designs.
Required Skills
- Proficient in Server Side Programming Languages :- PHP (Laravel)
- Proficient in design & architecting scalable products.
- Must have hands on experience in Ajax, Jquery.
- Database knowledge – MongoDb.
- Knowledge of Development Tools Bitbucket, Git, CI/CD with BitBucket and JIRA
- Web Server technologies:- Apache, Nginx
- Solid foundation in data structures, algorithms, and system design
- Expert in HTTP terminologies such as Request/Response cycle, content negotiation, CORS etc
- Management of hosting environment, including database administration and scaling an application to support load changes
- Optimization of the application for maximum speed and scalability
- Implementation of security and data protection
- Setup and administration of backups
- Obsess about code quality, automated testing, continuous integration, code reviews, and documentation.
- Exposure to microservices architecture/ API concepts would be an added advantage.
- Good organizational and time-management skills
Good To Have
- Knowledge of NodeJs, Angular
- Familiarity with AWS products - Beanstalk, Elb, ECS, EC2, SNS, SQS, S3, RDS, etc.
Qualifications
- Bachelor’s degree or equivalent in computer science / engineering
JOB SUMMARY
|
Job Title: |
Backend Web Application Developer (AWS Cloud) |
|
Team/Department: |
Omnicom Media Group IT (OMG – IT) |
|
Reporting: |
Manager – OMG IT |
|
Location: |
Bangalore |
ABOUT THE ROLE
THE ROLE IN SUMMARY
Omnicom Media Group (OMG) has an immediate opening for a highly motivated and talented backend web application developer, specializing in AWS cloud technologies. In this position you will be joining an in-house development team whose primary responsibility is developing new features and functionality for multiple existing web applications and day to day troubleshooting and issue resolution. The ideal candidate will possess excellent critical thinking and troubleshooting skills and have proven experience using popular AWS services commonly used to build serverless web application architectures. Candidates are expected to have strong knowledge of AWS API Gateway, Lambda, DynamoDB and Python programming. Familiarity with Cloud infrastructure as code frameworks, such as Serverless Framework, Terraform or CloudFormation, etc. is also required. Excellent English communication skills are a must as you will be a part of a team working alongside our primary development team in addition to several business analysis and project managers. 5+ years of prior backend and Cloud web application and software development experience required.
WHAT WILL YOU DO
KEY WORKING PRINCIPLES
- Passionate about modern web application architecture and programming. Hands on backend developer.
- Prior experience with modern RESTful API design and implementation. Microservices and single page web applications.
- Strong AWS knowledge, specifically serverless technologies (S3, API Gateway, Lambda, IAM, DynamoDB) as they relate to web application development.
- Excellent knowledge of web application security fundamentals (identity management, authentication, authorization, SSO).
- Designed several application databases in SQL and at least one non-relational database system, preferably
- Familiarity with DevOps practices including continuous integration and deployment, infrastructure as code in preferably Serverless Framework.
- Excellent verbal and written communication skills.
- 5+ years professional software development experience.
- Bachler’s degree in computer science or related field.
MUST HAVE SKILLS
- Backend Web Application Development
- Python
- AWS Services Including, CloudFront, S3, API Gateway, Lambda, Step Functions, SES, DynamoDB, Serverless Framework
- AWS Identity and Access Management principles (IAM)
- SQL (MS SQL Server, PostgreSQL, AWS Aurora or comparable)
- GIT, JIRA, Agile / Scrum
NICE TO HAVE SKILLS
- AWS Cognito






.png&w=256&q=75)


