Key Responsibilities
- Design and implement LLM powered video conversation systems to support use cases such as real-time customer service, sales enablement, and personalized product walkthroughs, integrating video streaming systems and leveraging multimodal models for speech. Text, and visual understanding.
- Develop and fine-tune LLM-driven solutions for tasks such as text summarization, customer support automation, personalization, and user journey understanding.
- Deploy LLM and ML models into production environments for activation across websites, product applications, and sales/marketing channels.
- Conduct comprehensive evaluation of LLMs, including performance benchmarking (accuracy, latency, token usage, cost), prompt effectiveness testing, fine-tuning impact analysis, and safety/bias assessments.
- Integrate LLM agents with APIs, internal knowledge bases, retrieval systems (RAG architectures), and external tools to enable autonomous or semi-autonomous decision-making.
- Build a deep understanding of business models, objectives, challenges, and opportunities by working closely with leadership and key stakeholders.
- Document model methodologies, evaluation frameworks, agent workflows, deployment architectures, and post-activation performance results in a structured and reproducible format.
- Stay current with advancements in LLMs, agentic AI, retrieval-augmented generation (RAG), and ML technologies to recommend and implement innovative solutions.
Key Skills
- Experience using Python, SciKit, SQL, Jupyter Notebooks, Amazon SageMaker, Github & AWS Bedrock.
- Experience working with multimodal AI systems for video-based conversation, speech-to-text, text-to-speech, and LLM-driven dialogue orchestration for interactive, real-time user engagement.
- Proven experience designing, fine-tuning, evaluating, and deploying Large Language Models (LLMs) and generative AI applications.
- Experience designing and deploying agentic systems using frameworks such as LangChain, AutoGen, CrewAI, and custom function-calling pipelines.
- Expertise integrating LLM agents with APIs, knowledge bases, retrieval systems (RAG architecture), and orchestrating dynamic multi-agent workflows.
- Strong understanding of evaluation metrics for LLMs, including prompt testing, token optimization, bias/safety analysis, latency, and cost benchmarks.
- Expertise in designing and executing A/B, multivariate, and lift tests to measure activated ML/LLM model performance across digital and offline channels.
- Continuous learner, keeping up-to-date with the latest advances in transformers, generative AI models, retrieval-augmented generation (RAG), and agentic AI frameworks.
Education and Experience
- B Tech or B. E. (Computer Science / Information Technology)
- 5 + years as a Data Scientist or similar roles.
Analytical and Personal skills
- Must have good logical reasoning and analytical skills.
- Good Communication skills in English – both written and verbal.
- Demonstrate Ownership and Accountability of their work.
- Attention to details.
