Senior Software Engineer- Python, LLM, GenAI

Location: Bengaluru

Time Type: Full time

Job Description

Job Description Summary

The Senior Software Engineer (AI/LLM) leads the design, development, and deployment of advanced AI and Generative AI capabilities within industrial software systems. You will work closely with data scientists, SMEs, and reliability engineers to implement ML/DL/AI solutions that improve operational efficiency, decision support, and user experience.
The role requires strong hands-on experience in Python and its API frameworks and experience building and validating ML/DL/AI solutions. Knowledge of industrial operations, Performance monitoring systems, or OT/IT data sources is a strong advantage.

Job Description

Roles and Responsibilities

ML/DL/AI Solution Development

• Design, develop, and implement AI-based solutions such as RAG pipeline, document query engines, semantic analysers.
• Build prompt orchestration, retrieval augmentation (RAG) solutions and context-management pipelines for industrial use cases.
• Develop scalable and secure solutions which utilize an GenAI based solution underneath to improve internal software systems.
• Optimize LLM inference performance, token usage, latency, and model selection based on functional and cost constraints.
• Implement validation frameworks for LLM outputs, including rule-based, statistical, or semantic validation, alignment checks, and performance monitoring.

• Support or lead development of ML models (classification, regression, anomaly detection, time-series insights) for reliability, operations, and maintenance use cases.
• Collaborate with data scientists to convert analytical logic into stable production code and cloud-ready services.
• Develop pipelines integrating historian/SCADA/CMMS/APM datasets into AI workflows.

Software Engineering & Integration

• Engineer robust backend services in Python with clean architecture, modular design, and high-quality code practices.
• Build and maintain REST APIs, microservices, and integration points with industrial systems and enterprise platforms.
• Work with product and domain teams to embed AI/LLM features directly into industrial software applications.
• Contribute to UI/UX workflows (optional) for AI-driven features such as chatbot interfaces, AI copilots, or operator assistance tools.

Quality, Validation & Governance

• Design automated evaluation frameworks for LLM results: hallucination checks, accuracy scoring, domain constraint validation, and response explainability.
• Maintain experiment tracking, version control, and model documentation to ensure reproducibility and governance.
• Support secure handling of operational and proprietary data with compliance to organizational and industry standards.
• Conduct performance testing, error monitoring, and continuous improvement of deployed AI services.

Collaboration & Innovation

• Partner closely with domain SMEs (maintenance, reliability, operations) to translate use cases into AI-driven workflows.
• Collaborate with platform/cloud engineering teams to deploy LLM services at scale (containers, serverless, GPU-enabled workloads).
• Actively explore new LLM capabilities, vector databases, fine-tuning methods, and industrial AI patterns, driving innovation in the team.
• Mentor junior developers and support internal AI capability-building initiatives.

Required Skills & Experience

• 5–8+ years of professional software engineering experience, including 2–3+ years building AI/ML or LLM-driven applications in production environments.
• Strong expertise in Python with deep experience in backend development, RESTful API design, and microservices architecture.
• 3+ years of hands-on experience with FastAPI, including strong knowledge of its architecture, performance optimization, dependency injection, and asynchronous capabilities.
• Demonstrated experience developing and deploying LLM-powered applications using frameworks such as OpenAI, Hugging Face, LangChain, LlamaIndex, or similar ecosystems.
• Proven ability to design and implement LLM validation frameworks, evaluation methodologies, guardrails, and prompt governance pipelines to ensure reliability, accuracy, and compliance.
• Solid understanding of LLM fundamentals, including tokenization, transformer architecture, attention mechanisms, embeddings, fine-tuning approaches, model constraints, and context window management.
• Experience managing the end-to-end ML lifecycle, including data preparation, model training, packaging, deployment, versioning, monitoring, and performance optimization.
• Familiarity with industrial or operational data systems (e.g., APM, historian systems, SCADA, CMMS/EAM) is highly desirable.
• Strong working knowledge of CI/CD practices and DevOps tooling, including Jenkins, Docker, Kubernetes, and Helm.
• Experience deploying and scaling applications on AWS, including infrastructure design and cloud-native architecture.
• Excellent analytical, problem-solving, and communication skills with the ability to collaborate effectively across engineering, product, and business teams.
• Exposure to frontend technologies such as Angular is a plus.

Education Qualification

• Bachelor's Degree in Computer Science or “STEM” Majors (Science, Technology, Engineering and Math) with advanced experience.

Additional Information