AI Platform Engineer, Business Applications

About the role

You will own the design and implementation of AI data foundations that power scalable generative AI use cases across Conga's business applications. This role involves owning end-to-end RAG pipelines, vector systems, and enterprise data integration workflows to enable intelligent features. You will build and optimize embedding strategies, vector indexing, and retrieval architectures that support real-time and batch AI workloads. You will collaborate closely with cross-functional teams to ensure that AI solutions are reliable, secure, and aligned with business objectives. A strong focus on data governance, including data access policies, masking, and compliance, will be central to your responsibilities. You will also ensure traceability and auditability of AI outputs while contributing to a culture of quality and continuous improvement. This position is ideal for someone who thrives in building platform capabilities that accelerate product innovation and deliver measurable AI impact at scale.

Key facts

What you'll do

Define and implement RAG pipelines including retrieval, ranking, and context injection to support advanced AI capabilities.

Optimize embedding strategies and vector indexing to improve data relevance, retrieval accuracy, and system performance.

Build real-time and batch data ingestion pipelines for structured and unstructured sources using scalable data integration patterns.

Develop scalable AI services using Python, FastAPI, and microservices architecture to support modular and reusable platform components.

Integrate AI platforms with enterprise systems such as CRM, knowledge bases, and data lakes to enable seamless data flow.

Enforce data governance by implementing data access policies, masking sensitive information, and ensuring compliance with standards.

Ensure traceability and auditability of AI outputs through robust logging, versioning, and monitoring mechanisms.

Deploy and operate cloud-native services with strong observability, including logging, monitoring, and AI-specific telemetry.

Contribute to AI platform reliability, scalability, and performance by applying MLOps practices and automation.

Partner with data scientists, product managers, and engineers to translate business requirements into scalable AI solutions.

Drive continuous improvement in retrieval accuracy, response quality, and efficiency of AI-driven systems.

Promote standardization and reuse of platform components to accelerate development and reduce redundancy across teams.

Support on-call responsibilities and collaborate with SRE and platform teams to ensure high availability and incident response.

Act as a technical leader in AI platform initiatives, mentoring peers and contributing to architectural decision-making.

Requirements

Bachelor's degree in engineering or equivalent.

Possess 3 to 5 years of experience in software development with a focus on AI development practices and design patterns.

Demonstrate hands-on experience with Python, FastAPI, PyTest, Celery, and related Python frameworks.

Show high-level familiarity with AI/ML, GenAI, and MLOps concepts and their practical applications.

Apply object-oriented programming, concurrency, and design patterns in production-grade software systems.

Work effectively with REST APIs and build services that are scalable, maintainable, and secure.

Have hands-on experience with RAG implementations, including prompt engineering, retrieval strategies, and vector databases.

Gain familiarity with containerization and orchestration tools such as Kubernetes and CI/CD tooling like Terraform and GitHub Actions.

Understand logging, monitoring, and AI observability practices, including tracing LLM calls, retrieval metrics, and model performance dashboards.

Bring experience with at least one major cloud service provider such as AWS, Microsoft Azure, or Google Cloud Platform.

Commit to adhering to data governance, security, and compliance requirements in all AI-driven implementations.

Demonstrate the ability to collaborate with cross-functional teams and communicate technical concepts clearly to both technical and non-technical stakeholders.

Show consistent focus on improving system efficiency, scalability, and reliability in data-intensive AI environments.

Nice to have

None specified.

Practical notes

The role is based in Bangalore, India. Engagement terms are specified as "See source" and may include details related to working hours, travel expectations, or visa requirements that are not detailed in this summary. Candidates should refer to the original source for specific operational expectations, including potential travel and administrative obligations associated with the position.