This role is for one of the Weekday's clients

**Salary range: Rs 3000000 - Rs 4000000 (ie INR 30 - 40 LPA)

**Min Experience: 4 years

Location: Bangalore

JobType: full-time

As a Senior GenAI Engineer, you will own the AI layer of our product, building intelligent features for enterprise clients. This is a production-focused role, emphasizing reliability, observability, and rigorous evaluations for AI systems. You will own the full vertical, from model to pipeline and UI, delivering high-impact features like CS Copilot and document understanding.

Key Responsibilities

Develop and take ownership of CS Copilot, including speech-to-text (STT) pipelines, real-time transcription, and LLM-driven recommendations.
Create LLM-based document comprehension features to extract structured data from unstructured enterprise documents.
Manage AI feature user interfaces end-to-end, encompassing both interface development and model integration.
Design and maintain an evaluation framework to measure AI feature quality and detect regressions.
Lead decisions on model selection and integration, balancing latency and cost considerations.
Ensure AI platform reliability by implementing observability, fallback mechanisms, and graceful degradation strategies.
Collaborate closely with product teams, customer success, and full-stack engineers to enhance usability and build trust.

Qualifications

At least 4 years of software development experience, including a minimum of 2 years dedicated to building and releasing production-grade AI/LLM features.
Bachelor’s or Master’s degree in Computer Science or a related technical discipline, or equivalent practical experience, with solid engineering fundamentals.
Proven ability to communicate complex AI challenges addressed, showcasing key insights and iterative improvements.
Expertise in engineering LLM pipelines, involving chaining, tool usage, structured output generation, and effective prompt management.
Experience managing the prompt lifecycle, including version control and rigorous testing.
Deep understanding and hands-on experience with Retrieval-Augmented Generation (RAG) fundamentals such as chunking, retrieval techniques, and embedding models.
Strong discipline in designing and implementing frameworks and metrics for AI evaluation.
Demonstrated skill in optimizing AI model latency and cost for production deployment.
Solid knowledge of Responsible AI principles and data privacy practices, especially relevant to enterprise data contexts.
Experience developing production-quality frontend user interfaces for AI features (e.g., using React).
Robust backend engineering capabilities for full-feature lifecycle ownership.
Experience in designing and implementing agentic systems, including multi-step agents and orchestration of tools.
Familiarity with voice and multimodal AI pipelines, including speech-to-text and real-time audio processing.
Practical experience with fine-tuning open-source models, such as LoRA and QLoRA.
Hands-on experience deploying open-source models on platforms like vLLM and Ollama.
Previous work experience in B2B SaaS or enterprise AI environments.
Domain knowledge in financial systems, billing platforms, or fintech applications.
Understanding of SaaS business models and applicable compliance frameworks.
Strong skills in API design and integration.
Experience working in a fast-paced startup setting.

Required Skills

Benefits & Perks

Competitive salary and equity (ESOPs).
Comprehensive health, dental, and vision insurance coverage.
Flexible paid time off policies and holidays.
Opportunities for professional growth and ongoing learning.
A dynamic and collaborative startup environment.

Skills

LLM Engineering, RAG AI Evaluation, Production AI Backend Development, React Model Deployment, Fine-tuning Responsible, AI API Design