
Senior Member of Technical Staff - SMTS
- Chennai, Tamil Nadu
- Permanent
- Full-time
- Contribute to accurate, unambiguous technical design specifications, including GenAI system integration and AI-enhanced workflows.
- Deliver customer value in the form of high-quality AI-powered software components and services, ensuring adherence to security, performance, longevity, and AI-driven automation best practices.
- Estimate the size of development tasks in story points, considering LLM inference latency and AI API rate limits.
- Understand and follow coding conventions, architectures, and best practices for GenAI-powered applications, LLM prompt engineering, and RAG (Retrieval-Augmented Generation) models.
- Write, debug, and deploy code to production, ensuring timely fixes for GenAI-based APIs, embeddings, and AI-driven microservices.
- Integrate and optimize OpenAI, Azure OpenAI, Hugging Face, LangChain, and LlamaIndex into enterprise applications.
- Leverage vector databases (Pinecone, FAISS, ChromaDB) for similarity search and AI retrieval pipelines.
- Adhere to Definition of Done (DOD) as part of the sprint, including:
- Unit tests, functional testing
- LLM performance benchmarking (BLEU, ROUGE, cosine similarity)
- AI model validation & API response optimization (temperature, top-k, max tokens)
- Code reviews, bug fixes, documentation
- Adherence to AI governance & responsible AI practices
- Learn domain-specific AI applications, including GenAI capabilities in automation, search, and AI-assisted decision-making.
- Take ownership of AI-enhanced product features, ensuring continuous model improvement and fine-tuning strategies.
- Contribute to agile ceremonies with a focus on AI-driven solutions and optimizations.
- Volunteer for GenAI-focused backlog items, such as:
- RAG model refinement
- Prompt engineering for better accuracy
- LLM evaluation and response optimization
- Participate in scrum meetings (daily stand-ups, sprint planning, readouts, retrospectives) with a focus on AI model iteration and feature scaling.
- Drive self-organization in AI workflows, ensuring GenAI is used effectively across teams.
- Work collaboratively across Technology, Product, AI/ML, and DevOps teams to align AI-driven enhancements with business goals.
- Build strong relationships with AI engineers, data scientists, and cloud architects to optimize LLM-based applications.
- Ensure AI compliance with security, ethical AI policies, and privacy standards (HIPAA, GDPR, SOC2, AI governance best practices).
- Train and mentor developers on GenAI integration, AI API usage, embeddings, and vector search optimizations.
- Guide the team on LLM prompt engineering, RAG model improvements, and API latency optimization.
- Encourage adoption of AI-enhanced developer workflows (e.g., Copilot, AI-assisted code generation, AI-powered testing).
- 5-10 years of experience in an engineering role, with exposure to AI/ML concepts.
- Experience in an Agile environment preferred.
- Bachelor’s Degree or equivalent in Computer Science, Engineering, or related field.
- Strong software engineering experience, including AI model integration and GenAI API workflows.
- Knowledge of modern programming language: Python (preferred for AI applications)
- Familiarity with Unix/Linux, Big Data, SQL, NoSQL, and AI data pipelines.
- Experience with AI frameworks and APIs such as OpenAI GPT, Hugging Face Transformers, LangChain, LlamaIndex.
- Exposure to retrieval-augmented generation (RAG), embeddings, and AI search optimization techniques.
- Understanding of vector databases (FAISS, Pinecone, ChromaDB) and similarity search models.
- Proficiency in cloud-based AI deployments (AWS or Azure OpenAI).
- Strong grasp of GenAI model evaluation techniques (BLEU, ROUGE, BERT Score, cosine similarity metrics).
- Ability to design and implement AI-powered solutions that improve software functionality.
- Problem-solving mindset to debug and optimize AI-generated responses.
- Ability to collaborate across AI, DevOps, and software engineering teams for seamless AI model integration.
- Experience in AI-driven feature development, from prompt engineering to embedding optimization.
- Ability to assess AI-generated content for bias, accuracy, and compliance.
- Strong analytical skills to measure AI model performance and recommend improvements.
- Curiosity and eagerness to explore new AI models, tools, and best practices for scalable GenAI deployment.