Backend Developer - Python & AI

About CustomerInsights.AI

CustomerInsights.AI is a global analytics and AI-driven company founded in 2018, enabling data-driven commercial decision-making for Life Sciences organizations. Our product ecosystem, including ciPARTHENON and ciATHENA, leverages Analytics Automation, Artificial Intelligence, and Machine Learning to deliver timely, actionable insights to key stakeholders. With teams across North America and India, we work with client organizations ranging from emerging startups to large enterprises.

Position Overview:

We are seeking a skilled professional with expertise in Generative AI to develop and implement AI-based applications for business use cases. This role involves close collaboration with key stakeholders to identify and define business problems, translate them into solution requirements, and drive effective outcomes. The individual will be responsible for delivering measurable business value, communicating insights, and presenting results to stakeholders. The role requires the ability to work on complex, unstructured business challenges and leverage data-driven approaches to build impactful solutions.

Key Responsibilities:

• Agentic AI & LLM Orchestration: Design, build, and maintain Agentic AI workflows using LangGraph / LangChain, including multi-agent coordination, tool invocation, memory, and state management.
• Develop deterministic and auditable agent flows suitable for enterprise-scale decisioning and analytics use cases. Implement prompt engineering strategies, guardrails, fallback mechanisms, and output validation to ensure reliable LLM responses.
• Backend & Platform Engineering : Architect and develop scalable Python-based backend services to support GenAI workloads. Build and expose APIs that integrate LLMs with structured and unstructured enterprise data sources. Ensure high availability, performance optimization, and fault tolerance across AI-driven backend systems.
• NL-to-SQL & Data Intelligence Design and implement NL-to-SQL pipelines for structured datasets across multiple business domains. Apply schema grounding, semantic layers, query validation, and SQL safety mechanisms to improve accuracy and trust. o Optimize generated queries for performance, explainability, and consistency across large datasets.
• Observability, Governance & Quality o Implement end-to-end observability for GenAI systems, including agent execution tracing, prompt/response logging, latency, and cost metrics. Define and monitor quality KPIs such as response accuracy, hallucination rates, and system reliability. Ensure compliance with enterprise security, privacy, and data governance standards.
• Cloud, Deployment & Operations (Azure): Design and deploy GenAI backend services on Azure using Azure OpenAI, AKS, Functions, and App Services.
• Implement CI/CD pipelines and infrastructure-as-code for scalable and repeatable AI deployments. o Partner with cloud and platform teams to optimize cost, scalability, and operational resilience.
• Documentation and Reporting: Document processes, pipelines, and architecture. Create clear and concise reports and dashboards to present findings and outcomes.

Required Skills:

• Expert-level proficiency in Python for backend development, APIs, and asynchronous processing
• Hands-on experience with LangGraph / LangChain for Agentic AI orchestration and workflow design
• Strong understanding of Large Language Models (LLMs), prompt engineering, tool calling, and response validation
• Experience designing and implementing Agentic AI systems with multi-agent coordination, memory, and state management
• Proven expertise in NL-to-SQL architectures, including schema grounding, semantic layers, and SQL validation
• Experience integrating LLMs with structured enterprise data sources and analytics platforms
• Strong experience with Azure cloud services, including Azure OpenAI, AKS, Functions, and App Services
• Experience building and deploying cloud-native microservices and RESTful APIs
• Knowledge of observability for GenAI systems, including logging, tracing, latency, and cost monitoring
• Experience implementing AI quality metrics such as accuracy, hallucination detection, and system reliability
• Familiarity with CI/CD pipelines, DevOps practices, and infrastructure-as-code
• Strong understanding of security, access control, and enterprise data governance
• Experience building scalable, fault-tolerant, production-grade platforms (beyond PoCs)
• Ability to d…