Senior Software Engineer

Client: Capgemini Location: Hyderabad Experience: 8+ Years Senior Software Engineer As a Senior Software Engineer, you will design, develop, test, and deploy sophisticated Generative AI applications. You will work within a dedicated engineering pod, partnering with technical leaders to translate architectural designs into robust, scalable, and secure software. This role requires hands-on development experience and a strong interest in solving complex technical problems using modern AI capabilities. In this role, you will: - Lead moderately complex initiatives and deliverables within technical engineering environments. - Contribute to large-scale planning of strategies across Consumer Technology. - Design, code, test, debug, and document applications and services, including upgrades and deployments. - Review technical challenges that require in-depth evaluation of technologies, procedures, and engineering approaches. - Resolve moderately complex issues while guiding teams to meet existing and emerging business needs. - Collaborate with peers, colleagues, and mid-level managers to resolve technical challenges and meet project goals. - Lead projects and act as an escalation point, providing direction to less experienced engineers. - Design, develop, and deploy AI applications using enterprise APIs, LLMs, agent frameworks, and related technologies. - Implement prompt engineering, retrieval-augmented generation, fine-tuning, and agentic design patterns. - Integrate LLM models with existing enterprise systems and ensure that AI solutions meet governance, security, and compliance standards. - Troubleshoot complex application and model-related issues and contribute to the continuous improvement of AI systems. - Assist and mentor engineers in advanced software development and AI engineering practices. - Stay informed of advancements in AI, LLMs, and agent frameworks and apply relevant updates to products and systems. Required Qualifications: - 4+ years of software engineering experience or equivalent through a combination of work experience, training, military service, or education. - 2+ years of experience working with Generative AI, large language models, or foundation models. - 2+ years of experience with either GCP, Azure, Kubernetes, or OpenShift. - 2+ years of experience with Python. - 2+ years of experience with REST API development and containerization technologies such as Docker and Kubernetes. - 2+ years of experience using Git for source code version control, including branching, pull requests, and collaborative development workflows. Desired Qualifications: - Understanding of cloud security principles including identity and access management, encryption, and network security in public or hybrid cloud environments. - Experience working in highly regulated industries such as financial services. - Experience as a technical lead or architect, including mentoring senior engineers. - Experience integrating or contributing to open-source AI or ML projects. - Experience integrating applications with enterprise data platforms, APIs, and secure data pipelines. - Strong communication and documentation skills to collaborate across engineering, product, and oversight teams. Preferred Skills and Experience: - Experience with LLM development using OpenAI, Anthropic, or Google Gemini models. - Experience with agentic frameworks and AI workflow orchestration. - Experience designing applications that incorporate retrieval-augmented generation, fine-tuning, and structured prompting. - Experience with vector databases and retrieval systems such as Elasticsearch, OpenSearch, Pinecone, or Weaviate. - Experience with LLM evaluation, observability, and monitoring, including latency, cost, accuracy, grounding, drift detection, and safety assessments. - Familiarity with ML lifecycle tools and processes such as feature stores, model registries, and CI/CD pipelines for AI services. - Familiarity with responsible AI principles, compliance, and governance processes related to AI systems in regulated environments. - Experience optimizing AI application performance, including prompt efficiency, model selection, caching, batching, and cost management. Skills:- Python, Google Cloud Platform (GCP), Docker, Generative AI (GenAI), Git and Large Language Models (LLM)