Design and implement advanced AI systems powered by large language models, focusing on autonomous reasoning, planning, and action through multi-agent architectures. Develop intelligent agents that integrate memory, tools, and function calling using frameworks such as LangChain, AutoGen, and Semantic Kernel, enabling secure and scalable interactions with external services.
Key Responsibilities
- Build and deploy agent-based AI solutions leveraging LLMs, dynamic tool orchestration, and Model Context Protocol (MCP) for reusable, secure interfaces
- Create voice-first agents using automatic speech recognition (ASR), natural language understanding, and high-fidelity text-to-speech (TTS) with real-time conversation flow
- Engineer Retrieval-Augmented Generation (RAG) pipelines using vector databases and Azure Cognitive Search to enhance response accuracy and context relevance
- Develop and optimize machine learning models for anomaly detection and fraud identification, supporting real-time inference and scalable deployment
- Deploy and monitor AI services on Microsoft Azure, utilizing Azure OpenAI, Functions, Service Bus, and Cosmos DB for resilient, cloud-native performance
- Collaborate across distributed engineering teams in India and the US, contributing to agile development cycles and technical mentorship
- Lead code reviews, support junior developers, and promote best practices in testability, scalability, and system reliability
Qualifications
- Bachelor’s degree or higher in Computer Science, Engineering, or a related technical field
- Minimum of 8 years of software engineering experience, with at least 2 years focused on production-level AI/ML systems
- Proven track record delivering LLM-driven or autonomous agent applications to production environments
- Hands-on experience with Azure AI services, including Cognitive Services, OpenAI, and serverless compute
- Strong Python proficiency and familiarity with ML frameworks such as PyTorch, scikit-learn, and Hugging Face
- Deep understanding of prompt engineering, context-aware execution, and tool integration patterns
- Experience with speech technologies (ASR/TTS), semantic search, and vector-based retrieval methods
- Background in fraud modeling, anomaly detection, or real-time inference pipelines
Technology Environment
Work with cutting-edge AI tools and platforms, including LLMs, RAG architectures, vector databases, and cloud-native services on Azure. Help shape the future of agentic experiences by enabling AI systems to securely interact with enterprise tools and services on behalf of users.
Work Model
This role operates in a hybrid work format, allowing flexibility in work location and environment. Alternative work arrangements are supported in alignment with evolving business needs.
Culture and Values
The organization fosters a culture rooted in inclusion, collaboration, and shared growth. Engineers are encouraged to innovate, mentor others, and contribute to a supportive environment where diverse perspectives drive better outcomes.
