Product Engineer / AIML 0 - 1 year (Chennai)

Freshers - Internship for 3 months Stipend: 10,000/month Duration: 3 Months Performance-based Full-Time Conversion This is a full on-site role you will be required to work from our office on all working days. Experienced CTC: 3 ~ 5 LPA About the Company Smartail is an innovative Artificial Intelligence-based company dedicated towards revolutionizing the education industry. Our flagship product, DeepGrade, is a cuttingedge AI software application that automates the grading of exam answer sheets in schools and colleges. By leveraging advanced technologies such as computer vision, deep learning, and natural language processing, DeepGrade excels in recognizing young adult handwriting and provides accurate grading for handwritten descriptive answers. It not only streamlines the grading process but also enhances learning, pedagogical decision-making, assessment, and feedback for educational institutions. As a unique and pioneering product, DeepGrade sets a new standard in the education sector, transforming the way educators and students interact with assessment and feedback. About the Role As a Product Engineer, you will sit at the intersection of engineering and product thinking building, iterating, and shipping AI-powered features that directly impact end users. You will work closely with product managers, designers, and data scientists to translate ideas into robust, production-grade software, with a strong emphasis on integrating large language models, machine learning pipelines, and third-party APIs into scalable products. This role is ideal for engineers who think like product builders not just writing code, but asking why , obsessing over user experience, and taking end-to-end ownership of features from concept to launch. Work Location & Schedule Location: Chennai, Tamil Nadu (On-site) This is a full-time, in-office role based at our Chennai office. We believe in the energy and collaboration that comes from working together in person candidates must be based in Chennai or willing to relocate prior to joining. - No remote or work-from-home option all employees are expected to be present at the office on all working days - Working days: Monday to Friday + alternate Saturdays (working Saturdays follow a fixed roster shared at the start of each month) - Candidates currently outside Chennai are welcome to apply, provided they can relocate before the joining date at their own arrangement Key Responsibilities - Design, develop, and deploy AI/ML-powered product features using Python and modern frameworks - Build and maintain integrations with LLM APIs (e.g., OpenAI, Anthropic, Gemini) and other third-party services via REST/GraphQL APIs - Write, test, and iterate on prompts for LLM-based features, including system instructions, few-shot examples, and output parsers - Collaborate with product and design teams to translate user requirements into technical specifications and working software - Evaluate model outputs for quality, reliability, and safety; implement guardrails and fallback logic as needed - Instrument features with logging, monitoring, and analytics to enable data-driven product decisions - Participate in code reviews, sprint planning, and technical design discussions - Stay current with rapidly evolving AI/ML tooling and bring relevant innovations to the team QualificationsMust-Have - 01 years of professional software development experience - Strong proficiency in Python clean, testable, production-quality code - Exposure to ML concepts Computer Vision & Object Detection, Transformers & NLP, fine-tuning, embeddings, RAG (Retrieval-Augmented Generation), vector databases (Pinecone, Weaviate, pgvector) - Hands-on experience working with LLM APIs (OpenAI, Anthropic Claude, Google Gemini, or similar) - Demonstrated prompt engineering skills crafting, evaluating, and refining prompts for real product use cases - Experience building and consuming RESTful ; familiarity with API authentication patterns (OAuth, API keys, JWT) - Solid understanding of software engineering fundamentals data structures, version control (Git), testing, and debugging Positive to Have - Experience with LLM orchestration frameworks such as LangChain, LlamaIndex, or similar - Familiarity with cloud platforms ( AWS, GCP, or Azure ) and deploying services in containerized environments (Docker, Kubernetes) - Knowledge of evaluation frameworks for LLM outputs (RAGAS, custom evals, human feedback loops) - Prior experience working in an agile/scrum product team Soft Skills - Strong product intuition ability to connect technical decisions to user outcomes - Excellent written and verbal communication; able to explain AI behavior to non-technical stakeholders - Comfortable with ambiguity and rapid iteration in a fast-paced environment - Collaborative, curious, and proactive about ownership. Freshers Internship Details Duration: 3 Months Stipend: 10,000 per month