AI Engineer

Comviva Technology; Gurugram District; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Comviva Technology is seeking an experienced AI/ML Engineer to design and implement AI-powered features for its MarTech products. You will craft intelligent agents, pipelines, and integrations using LLMs, embeddings, and vector search, aligning with enterprise standards.

Collaborate with product managers, architects, and developers to translate requirements into scalable AI solutions and ensure performance, security, and reliability in production environments.

Qualifications

• Bachelor’s degree in Computer Science, IT, AI, Data Science or a related field.

Responsibilities

• Design, develop, and implement AI-powered features for MarTech products.
• Build AI workflows and agent-based solutions for campaign assistance and segmentation.
• Collaborate with product managers and engineers to translate requirements into technical designs.
• Develop and integrate solutions using LLMs, embeddings, vector search, and RAG techniques.
• Ensure scalable, secure, and production-ready AI implementations with performance focus.

Skills

Python

AI/ML

Generative AI

Prompt engineering

Embeddings

Semantic search

LLM architectures

API integration

Cloud platforms

Agile

Education

Bachelor's degree in Computer Science / IT / AI / Data Science

Tools

LangChain

LangGraph

LlamaIndex

Semantic Kernel

CrewAI

Job description

Key Accountabilities

• Design, develop, and implement AI-powered features, assistants, and agents for our MarTech products.
• Build intelligent agentic workflows for use cases such as campaign assistance, offer recommendations, segmentation support, customer insights, reporting assistance, troubleshooting, and knowledge discovery.
• Work with product managers, architects, developers, and business teams to understand requirements and convert them into scalable AI solutions.
• Develop and integrate solutions using Large Language Models, prompt engineering, embeddings, vector search, and retrieval-augmented generation techniques.
• Create and maintain AI workflows involving context handling, memory patterns, tool integration, guardrails, and response optimization.
• Build AI pipelines using enterprise product knowledge, technical documentation, support content, metadata, and domain data.
• Integrate AI services with backend applications, APIs, microservices, workflow engines, and enterprise systems.
• Develop reusable AI components and frameworks that can be adopted across multiple modules and use cases within our product lines.
• Evaluate AI solution quality using testing, benchmarking, observability, feedback loops, and output validation techniques.
• Ensure AI implementations are scalable, secure, reliable, and optimized for latency, cost, and performance in production environments.
• Work closely with DevOps and platform teams to deploy, monitor, and manage AI solutions in cloud-native environments.
• Collaborate with QA and security teams to validate AI features, reduce risks, and ensure compliance with enterprise standards.
• Support the end-to-end development lifecycle of AI-powered product capabilities, from ideation and prototyping to deployment and continuous improvement.
• Identify opportunities to improve product capability, team productivity, and customer value through the effective use of AI and intelligent automation.
• Stay updated on advancements in Generative AI, agent frameworks, LLMOps, and enterprise AI engineering practices.

Mandatory Skills

• Bachelor s degree in Computer Science, Information Technology, Artificial Intelligence, Data Science, Engineering, or a related field.
• Minimum of 4-8 years of experience in software engineering, with at least 2 years of relevant experience in AI/ML, Generative AI, or intelligent application development.
• Strong programming skills in Python and good understanding of production-grade software development practices.
• Hands-on experience in building applications using Large Language Models and Generative AI platforms.
• Proven experience in prompt engineering, embeddings, semantic search, vector databases, and retrieval-augmented generation architectures.
• Experience in designing and developing AI assistants, copilots, chatbots, or agent-based enterprise applications.
• Strong understanding of APIs, backend integrations, microservices, and enterprise application integration patterns.
• Ability to translate functional and business requirements into clear technical solutions and implementation designs.
• Knowledge of model evaluation, AI testing, hallucination reduction, grounding techniques, and response quality validation.
• Familiarity with cloud platforms such as AWS, Azure, or GCP and deployment practices for AI-enabled applications.
• Understanding of containerization, CI/CD, monitoring, observability, and production support practices.
• Strong analytical, problem-solving, and debugging skills.
• Good communication skills with the ability to collaborate effectively with both technical and non-technical stakeholders.
• Knowledge of Agile development methodologies and product engineering practices.

Desirable Skills

• Experience in telecom, MarTech, loyalty, customer engagement, campaign management, or customer data platforms.
• Familiarity with AI orchestration and agent development frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, or similar tools.
• Exposure to Java, Spring Boot, Node.js, Kafka, event-driven architecture, and microservices-based enterprise systems.
• Experience with vector stores, caching layers, and AI observability or LLMOps tools.
• Understanding of recommendation systems, personalization, decisioning platforms, or analytics-driven applications.
• Familiarity with enterprise AI governance, PII protection, security controls, and responsible AI practices.
• Experience working in collaborative and cross-functional product engineering teams.
• Understanding of end-to-end enterprise AI architecture and production deployment considerations.