Lead AI Application Engineer - AI Research & Innovation

Avaya; Pune District; On-site; INR 5,200,000 - 8,500,000; Full time

Job summary

Avaya is seeking a highly experienced Lead AI Application Engineer to design, develop, and deploy advanced Machine Learning, Generative AI and Agentic AI applications in high-throughput real-time streaming environments. You will lead complex autonomous AI initiatives, shaping production-grade AI systems and setting a technical direction for the AI team.

The ideal candidate has 15+ years of software development experience, with 5+ years deploying Generative and Agentic AI in production, deep

Responsibilities

• Architect and operationalize end-to-end autonomous agentic systems (multi-agent orchestration, dynamic tool-calling, reflection, planner-executor loops, and persistent state management).
• Design robust LLM runtime infrastructure, including hybrid retrieval architectures (Advanced RAG, graph-based context grounding, vector databases, re-rankers, semantic routing).
• Establish scalable evaluation, guardrail, and observability frameworks (latency optimization, cost governors, hallucinations/drift detection, alignment checks, red-teaming).
• Make high-stakes architectural decisions regarding model topologies (proprietary frontier models vs. distilled/fine-tuned SLMs, LoRA, quantization, self-hosted vs. managed endpoints).
• Lead from the front: write high-leverage production code, design critical framework primitives, and rapidly de-risk zero-to-one concepts via functional PoCs.
• Bridge cutting-edge research and production engineering, ensuring systems are resilient, fault-tolerant, secure, and performant at scale.
• Partner directly with the Head of AI, Product leadership, and VP-level stakeholders to chart the AI technology roadmap and identify transformative capability unlocks.
• Lead the exploration and application of Large Language Models, Agentic AI and Generative AI, venturing into new areas within these fields.
• Represent the company’s AI thought leadership through open-source contributions, technical papers, conferences, or industry forums.
• Architect, Design and Build robust, scalable, and efficient AI systems leveraging a variety of AI/ML, data science, deep learning, and agentic AI frameworks.
• Drive the integration of complex Model Context Protocol (MCP) and agent-to-agent (A2A) communication protocols, ensuring seamless interaction and optimal performance.
• Design and implement scalable and efficient AI/ML systems, architectures, and pipelines that can handle large volumes of data and deliver accurate and timely results.
• Regularly self-educate while mentoring and provide technical leadership to other engineers, fostering a culture of continuous learning and excellence.

Job description

About Avaya

Avaya is an enterprise software leader that helps the world’s largest organizations and government agencies forge unbreakable connections.

About Avaya

Avaya is an enterprise software leader that helps the world’s largest organizations and government agencies forge unbreakable connections. The Avaya Infinity™ platform unifies fragmented customer experiences, connecting the channels, insights, technologies, and workflows that together create enduring customer and employee relationships. We believe success is built through strong connections – with each other, with our work, and with our mission. At Avaya, you'll find a community that values your contributions and supports your growth every step of the way. Learn more at https://www.avaya.com

Job Information

Job Code: 00194005 Job Family: Research and Development Job Function: Software Engineering

About The Role

We are seeking a highly experienced and visionary Lead AI Application Engineer to join our core AI team. This pivotal role will be instrumental in designing, developing, and deploying advanced Machine Learning, Generative AI and Agentic AI applications across high-throughput, real-time streaming environments . You are an engineer’s engineer, someone who spent years training, tuning, and deploying models at scale, and who has spearheaded Generative and Agentic AI over the last 3–4 years. This is an exceptional opportunity for an individual who thrives on building sophisticated, production-grade Autonomous AI systems and wants to make a significant impact.

Key Responsibilities

Technical Architecture & System Design

• Architect and operationalize end-to-end autonomous agentic systems (multi-agent orchestration, dynamic tool-calling, reflection, planner-executor loops, and persistent state management).
• Design robust LLM runtime infrastructure, including hybrid retrieval architectures (Advanced RAG, graph-based context grounding, vector databases, re-rankers, semantic routing).
• Establish scalable evaluation, guardrail, and observability frameworks (latency optimization, cost governors, hallucinations/drift detection, alignment checks, red-teaming).
• Make high-stakes architectural decisions regarding model topologies (proprietary frontier models vs. distilled/fine-tuned SLMs, LoRA, quantization, self-hosted vs. managed endpoints).

Hands-On Execution & Prototyping

• Lead from the front: write high-leverage production code, design critical framework primitives, and rapidly de-risk zero-to-one concepts via functional PoCs.
• Bridge cutting-edge research and production engineering, ensuring systems are resilient, fault-tolerant, secure, and performant at scale.

Strategy & Cross-Functional Influence

• Partner directly with the Head of AI, Product leadership, and VP-level stakeholders to chart the AI technology roadmap and identify transformative capability unlocks.
• Lead the exploration and application of Large Language Models, Agentic AI and Generative AI, venturing into new areas within these fields.
• Represent the company’s AI thought leadership through open-source contributions, technical papers, conferences, or industry forums.

Other Responsibilities

• Architect, Design and Build robust, scalable, and efficient AI systems leveraging a variety of AI/ML, data science, deep learning, and agentic AI frameworks.
• Drive the integration of complex Model Context Protocol (MCP) and agent-to-agent (A2A) communication protocols, ensuring seamless interaction and optimal performance.
• Design and implement scalable and efficient AI/ML systems, architectures, and pipelines that can handle large volumes of data and deliver accurate and timely results.
• Regularly self-educate while mentoring and provide technical leadership to other engineers, fostering a culture of continuous learning and excellence.

Who We Are Looking For -

• Experience: 15+ years of hands-on software development experience, including 5+ years actively building and deploying Generative AI and Agentic AI applications in production.
• Core Engineering & AI Building: Hands-on builder capable of independently architecting, coding, and deploying custom AI tools, autonomous agents, and bots from scratch.
• Programming Mastery: 8+ years writing production-grade code in Python or similar languages with deep expertise in scalable software design, APIs, and microservices.
• Agentic Frameworks & Tools: Deep proficiency with frameworks such as LangChain, LlamaIndex, Auto-GPT, CrewAI, and Model Context Protocol (MCP) for multi-agent coordination.
• LLMs & Fine-Tuning: Practical experience with frontier models (GPT-4, Gemini, Claude), fine-tuning, prompt engineering, and custom agentic tool-calling workflows.
• ML/DL Foundations: Background in training, tuning, and running models using PyTorch, TensorFlow, or Scikit-learn in high-throughput environments.
• Inference & Acceleration: Familiarity with inference engines (vLLM, TensorRT-LLM, TGI) and cloud ML infrastructure (NVIDIA GPUs, TPUs).
• Data & Memory Infrastructure: Experience building low-latency vector search indices, in-memory caching layers, streaming pipelines (Kafka/Flink), and NoSQL datastores to power real-time agent context and memory.
• Education: Master's or Ph.D. in Computer Science, AI, ML, or a related quantitative field (or equivalent practical experience).

Knowledge, Skills, And Abilities

• Autonomous Execution: Proven track record as a senior IC who takes total ownership—from zero-to-one prototyping to production rollout.
• Cloud & DevOps: Exposure to AWS, Azure, or GCP environments with modern containerized deployment (Kubernetes, Docker).
• Domain & Communication: Experience in contact center/telecom/CX platforms is a plus; excellent technical communication skills required.

Experience

12+ Years of Experience

Education

• Bachelor degree or equivalent experience
• Advance Degree preferred in Computer Science or Related Field

Footer

Applicants must be currently authorized to work in the United States without the need for visa sponsorship now or in the future.

Avaya is an Equal Opportunity employer and a U.S. Federal Contractor. Our commitment to equality is a core value of Avaya. All qualified applicants and employees receive equal treatment without consideration for race, religion, sex, age, sexual orientation, gender identity, national origin, disability, status as a protected veteran or any other protected characteristic. In general, positions at Avaya require the ability to communicate and use office technology effectively. Physical requirements may vary by assigned work location. This job brief/description is subject to change. Nothing in this job description restricts Avaya right to alter the duties and responsibilities of this position at any time for any reason.