Job Description : Generative AI Engineer
Location : Pune
Experience : 1-4 years
Role Overview
We are looking for a Generative AI Engineer who will design, build, deploy, and maintain large language model (LLM)-based solutions. This engineer will work closely with architecture, data science, product, and operations teams to integrate GenAI capabilities into our insurance business processes — such as claims automation, intelligent customer support, underwriting, fraud detection, policy servicing, knowledge management, etc.
Key Responsibilities
- Design, build, and deploy solutions using large language models (open source and / or proprietary) to address insurance domain use-cases (e.g. document understanding, claims summarization, question answering, policy retrieval, chatbots).
- Evaluate, select, fine-tune, and optimize LLMs for latency, accuracy, cost, security, and compliance.
- Work on prompt engineering, data preparation, annotation, and feedback loops to improve model performance.
- Model monitoring, performance metrics, bias detection, maintenance of model drift, guardrails.
- Architecting GenAI solutions on cloud infrastructure (AWS / Azure / GCP / hybrid) ensuring scalability, reliability, cost effectiveness, and security.
- Integrate GenAI components into existing systems (APIs, microservices, UI / UX interfaces) and pipelines.
- Ensure data privacy, regulatory compliance (IRDAI, etc.), and internal security standards in handling sensitive data.
- Collaborate with cross-functional teams : product, legal / compliance, IT ops, data engineering, UX.
- Stay up to date with the latest developments in generative models, LLMs, and AI / ML best practices.
Required Skills & Experience
Must-haves
Experience in building and deploying NLP / LLM / GenAI projects.Solid understanding of cloud architecture : compute, storage, networking, serverless / containers / Kubernetes.Hands-on with one or more LLM platforms / frameworks : OpenAI, Anthropic, Hugging Face, Llama / OpenLlama, etc.Experience with fine-tuning / prompt engineering / evaluating LLMs (metrics, biases, hallucinations).Strong programming skills : Python, possibly some experience with Java / Scala / etc.Experience building APIs, microservices, integrating models into production pipelines.Familiarity with insurance regulations, data privacy laws in India.Good knowledge of ML engineering / MLOps : versioning, CI / CD, model monitoring, logging.Ability to work with unstructured data (documents, PDFs, scanned images) and preprocess / clean / extract information.Nice-to-haves
Experience in insurance domain (claims, underwriting, risk management).Experience with multi-modal models (e.g. images + text) or vision-language models.Experience with multilingual LLMs (especially Indian languages).Familiarity with responsible AI / ethics, model interpretability.Prior experience deploying large models on edge or offline settings.Experience with cloud cost optimization for AI workloads.Skills in frontend integration (for chatbot or user-facing UI).Qualifications
Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, Machine Learning, or related field.Proven track record of shipping AI / ML systems, ideally with visible metrics showing impact.Strong communication skills, ability to explain technical concepts to non-technical stakeholders.