Lead Software Engineer - AI & Python

Job Description

Key Responsibilities:

• Lead the development of robust, high-performance web and generative AI applications.
• Build and deploy GenAI solutions leveraging Retrieval-Augmented Generation (RAG) pipelines for intelligent document querying, summarization, and semantic search.
• Extract, structure, and process data from complex documents (PDFs, images, scanned forms) using integrated OCR engines (e.g., Tesseract, PaddleOCR) and vision-language models.
• Develop RAG-based GenAI applications using tools like LangChain and LlamaIndex, and work with vector databases (e.g., FAISS, Weaviate) for efficient embedding-based retrieval.
• Integrate OCR, LLMs, and vector search into business applications to automate the extraction, understanding, and processing of unstructured content.
• Design, train, and optimize both Small Language Models (SLMs) and Large Language Models (LLMs) for domain-specific applications, ensuring efficiency and high performance.
• Develop scalable training pipelines leveraging methods such as supervised fine-tuning, reinforcement learning from human feedback (RLHF), prompt tuning, parameter-efficient fine-tuning (e.g., LoRA, adapters), and knowledge distillation.
• Fine-tune, evaluate, and deploy language models using advanced techniques like quantization, continual learning, and model distillation to meet evolving business requirements.
• Analyze and monitor model outputs for quality, bias, and safety, iterating to improve accuracy and model alignment with user and business needs.
• Architect, design, and implement scalable and secure solutions aligned with business objectives.
• Mentor and guide a team of developers, fostering a culture of continuous learning and improvement.
• Design and maintain APIs, including RESTful and GraphQL interfaces, ensuring seamless data exchange with third-party services.
• Implement and maintain CI/CD pipelines, utilizing automation tools for seamless deployment.
• Collaborate with cross-functional teams, including DevOps, Security, Data Science, and Product Management.
• Optimize application performance by efficiently managing resources, implementing load balancing, and optimizing queries.
• Ensure compliance with industry security standards such as GDPR.
• Stay updated with emerging technologies, especially in Generative AI, Machine Learning, cloud computing, and microservices architecture.

Required Qualifications:

• Bachelor’s or master’s degree in computer science, Engineering, or a related field.
• 6+ years of hands-on experience in AI & Python development, with expertise in Django, Flask, or FastAPI.
• Ability to design and build end-to-end applications and API integrations
• Proven experience with large language models (LLMs) and AI model development
• Experience with developing retrieval-augmented generation (RAG).
• Experience with GenAI tools like Langchain, LlamaIndex, LangGraph, and open-source Vector DBs.
• Exposure to prompt engineering principles and techniques like chain of thought, in-context learning, tree of thought, etc.
• Exposure to SLMs.
• Experience with supervised fine-tuning, reinforcement learning from human feedback (RLHF), prompt tuning, parameter-efficient fine-tuning (e.g., LoRA, adapters), and knowledge distillation.
• Experience with relational databases such as MS SQL Server, PostgreSQL, and MySQL.
• Expertise in DevOps practices, including Docker, Kubernetes, and CI/CD tools like GitHub Actions.
• Deep understanding of microservices architecture and distributed computing principles.
• Strong knowledge of security best practices in software development.
• Familiarity with data analytics and visualization tools such as Snowflake, Looker, Tableau, or Power BI.
• Excellent problem-solving skills and the ability to work independently and within a team.
• Strong communication and stakeholder management skills.