AI Agent Observability Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Agent Observability Engineer based in India.
This opportunity is designed for an early-career engineer interested in building software and applying artificial intelligence to real-world products and platforms. You will contribute to backend and full-stack development while gaining hands-on exposure to AI and Large Language Model (LLM) capabilities. Working alongside experienced engineers, you will help design, test, deploy and monitor production-ready systems. The role combines software engineering fundamentals with practical work across LLM integrations, Retrieval-Augmented Generation (RAG), evaluation and agent capabilities. You will also contribute to automated testing, datasets, benchmarks and observability to improve system quality and reliability. This is a fast-paced environment where you can develop technical skills, collaborate with global teams and build practical experience in emerging technologies.
Accountabilities
Contribute to backend and full-stack feature development, testing and releases for core products and platforms, delivering production-ready code.
Collaborate with senior engineers on module design, API and interface definition, system integration and deployment.
Support logging, monitoring, troubleshooting and performance optimisation across deployed services.
Write and maintain automated tests and Continuous Integration and Continuous Delivery (CI/CD) configurations to improve development efficiency and code quality.
Support the integration and deployment of Artificial Intelligence (AI) and Large Language Model (LLM) capabilities based on business requirements.
Integrate LLM application programming interfaces (APIs), develop basic Retrieval-Augmented Generation (RAG) pipelines and embed tools or agent capabilities into existing systems.
Help build and maintain datasets and benchmarks for AI evaluation and regression testing.
Track online system and model performance, assist with debugging and contribute to resolving technical issues.
Produce clear technical documentation and communicate effectively with engineering and cross-functional teams.
Requirements
Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Software Engineering, Artificial Intelligence or a related field.
Strong software engineering fundamentals, including data structures and algorithms, object-oriented design, common design patterns and coding best practices.
Proficiency in Python is required, along with experience using at least one primary programming language for engineering work.
Experience with Java, Go, TypeScript or JavaScript is a plus.
Familiarity with Git, basic Linux environments and software debugging practices.
Understanding of unit and integration testing, Representational State Transfer (RESTful) APIs and relational or non-relational databases.
Some project or internship experience with AI or LLM technologies is sufficient; deep research experience is not required.
Familiarity with prompt engineering, function calling, RAG, vector databases or frameworks such as LangChain or LangGraph is a plus.
Strong ownership and accountability, with the ability to take initiative and deliver assigned work.
Good communication and collaboration skills, with the ability to work effectively with senior engineers and cross-functional teams.
Ability to learn quickly and adapt to new technologies, tools and engineering practices.
Experience shipping web or backend services is a plus.
Knowledge of caching, message queues, concurrency and performance tuning is a plus.
Familiarity with Docker, Kubernetes, cloud platforms such as AWS, Google Cloud Platform (GCP) or Microsoft Azure, or observability tools such as Prometheus, Grafana or ELK is a plus.
Exposure to LLM evaluation, prompt iteration, data feedback loops or basic fine-tuning workflows is a plus.
Able to commit to at least 6 months, 5 days per week.
Benefits
3–6 month early-career internship opportunity with potential for continued engagement based on business needs and applicable local laws.
Work-from-home arrangement, subject to the nature of the business team.
Opportunity to gain hands-on experience in blockchain, digital assets, AI and LLM technologies.
Exposure to backend and full-stack software development and production engineering.
Collaboration with experienced engineers and global teams.
Opportunities for networking and professional development.
Experience working on fast-paced, innovative projects with autonomy and meaningful technical challenges.
Continuous learning and opportunities for career development.
Competitive salary and company benefits.
Opportunity to develop transferable technical and professional skills in a global technology environment.
How Jobgether Works
We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.
We appreciate your interest and wish you the best!
Why Apply Through Jobgether?
Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.
We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.

Work arrangement
No