GenAI and Agentic AI Specialist

‍

We are looking for a passionate and experienced GenAI and Agentic AI Specialist to join our Voice Agentic AI Platform team. In this role, you will architect, build, and deploy intelligent voice agents powered by large language models (LLMs) and generative AI technologies. You will drive end-to-end development of agentic workflows, integrate speech-to-text (STT) and text-to-speech (TTS) capabilities, and contribute to fine-tuning and deployment of domain-specific AI models. Working at the intersection of conversational AI, voice automation, and LLM engineering, you will help define the next generation of intelligent customer engagement solutions.

‍

Voice Agentic AI Development

• Design and implement end-to-end voice agent pipelines integrating LLMs, STT/TTS models, and telephony systems.
• Build agentic decision trees, conversational flows, and multi-turn dialogue management for real-world use cases like payment reminders, outbound campaigns, and customer support automation.
• Leverage frameworks such as LangChain, LlamaIndex, or equivalent agentic orchestration tools to build robust, production-grade voice agents.

‍

Generative AI & LLM Engineering

• Architect and develop GenAI solutions using foundational models (e.g., GPT, Mistral, LLaMA, Gemini) for NLU, intent classification, slot filling, and context-aware response generation.
• Implement prompt engineering, retrieval-augmented generation (RAG), and structured output strategies to maximize accuracy and reliability.

‍

Model Fine-Tuning & Adaptation

• Lead or contribute to fine-tuning LLMs and domain-specific STT/TTS models using techniques such as LoRA, QLoRA, or full fine-tuning on curated datasets.
• Manage training pipelines, evaluate model performance with appropriate metrics, and iterate based on real-world feedback.
• Collaborate with data teams to build high-quality annotated datasets for supervised and reinforcement learning from human feedback (RLHF).

‍

Model Deployment & MLOps

• Deploy models to cloud or on-premise environments, ensuring scalability, reliability, and low-latency performance.
• Utilize tools such as vLLM, TorchServe, Triton Inference Server, or HuggingFace Inference Endpoints for model serving.
• Implement model versioning, A/B testing, monitoring, and rollback mechanisms to maintain production stability.

‍

Platform Integration & Orchestration

• Integrate voice agents with telephony platforms (e.g., LiveKit, Twilio, Asterisk) and backend systems such as CRM, billing, and campaign management tools.
• Develop APIs and middleware for seamless communication between AI components, voice infrastructure, and business logic layers.
• Ensure robust handling of edge cases, error recovery, and fallback strategies in live environments.

‍

Inferencing Pipeline (Optional)

• Contribute to designing and optimizing real-time and batch inferencing pipelines for STT, LLM, and TTS components.
• Implement strategies for latency reduction, throughput optimization, and cost management across the inference stack.
• Research & Innovation
• Stay current with advancements in generative AI, agentic AI, and voice technologies.
• Evaluate new models, tools, and techniques to enhance platform capabilities.
• Document architectures, experiments, and best practices to build institutional knowledge.

‍

• 4–5 years of experience in AI/ML engineering with a strong focus on Generative AI, LLM-based systems, and conversational or voice AI.
• Bachelor’s or master’s degree in computer science, Artificial Intelligence, Data Science, or a related field.
• Strong problem-solving mindset with a bias for execution, experimentation, and continuous learning.
• Ability to work independently and collaboratively in a fast-paced, agile environment.
• High ownership and accountability for the quality, reliability, and performance of AI systems in production.
• Strong communication skills to articulate complex AI concepts to both technical and nontechnical stakeholders.
• Hands-on experience with agentic AI frameworks (LangGraph, AutoGen, CrewAI, or equivalent) and designing multi-step agent workflows.
• Proficiency in Python and familiarity with ML frameworks such as PyTorch, TensorFlow, or JAX.
• Experience in fine-tuning large language models using parameter-efficient techniques (LoRA, QLoRA) or full fine-tuning pipelines.
• Demonstrated ability to deploy AI models to production environments using cloud platforms (AWS, GCP, Azure) or on-premises infrastructure.
• Familiarity with STT (e.g., Whisper, Google STT, Azure Speech) and TTS (e.g., ElevenLabs, Coqui, Azure TTS) model ecosystems.
• Experience with telephony integration or voice platforms (LiveKit, SIP-based systems) is a strong advantage.
• Knowledge of MLOps practices including model versioning, CI/CD for ML, monitoring, and evaluation pipelines.
• Exposure to inferencing optimization tools (vLLM, Triton, ONNX Runtime) is a plus.
• Preference for candidates from product companies or large-scale AI platform environments.

‍

• Impactful Work: Play a pivotal role in safeguarding Tanla's assets, data, and reputation in the industry.
• Tremendous Growth Opportunities: Be part of a rapidly growing company in the telecom and CPaaSspace, with opportunities for professional development.
• Innovative Environment: Work alongside a world-class team in a challenging and fun environment, where innovation is celebrated.

‍

Tanla is an equal opportunity employer. We champion diversity and are committed to creating an inclusive environment for all employees.