Job Overview

Cisco is hiring a Software Engineer for an Agentic AI and LLM-focused role in Bangalore. The position combines Python backend engineering, machine learning engineering, applied artificial intelligence, distributed systems, cloud architecture, data pipelines, and modern AI application development.

The engineer will help design scalable systems for Agentic AI and large language model workloads, with a strong focus on LangGraph and retrieval-augmented generation architectures. The role also involves productionizing AI systems, improving model and application performance, and building reliable cloud-native infrastructure on AWS.

This is a senior engineering opportunity for professionals who can work across backend, data, cloud, and AI platforms while contributing to technical architecture and engineering standards. The role requires strong hands-on experience and the ability to solve complex technical and production problems.

Key Responsibilities

• Design scalable Python backend services and data pipelines that support AI and machine learning applications.
• Develop complex Agentic AI and LLM systems using LangGraph and related architectural approaches.
• Build and improve Retrieval-Augmented Generation architectures for production use cases.
• Define approaches for improving LLM token usage, latency, throughput, performance, and operating cost.
• Establish engineering standards for AI and RAG architectures, APIs, databases, and distributed systems.
• Design and operate cloud-native solutions on AWS using services such as S3, SQS, SNS, and Lambda.
• Support containerized workloads using Docker and Kubernetes.
• Operationalize deep learning and LLM models for production environments.
• Implement versioned prompts, runtime safeguards, and rollback strategies for LangGraph and multi-agent workloads.
• Evaluate AI applications and improve their reliability using LLM evaluation and observability tools.
• Optimize ETL workloads through scheduling, partition pruning, caching, and storage-format improvements.
• Investigate and resolve complex technical and production issues across engineering teams.
• Work with stakeholders to connect technical strategy with business objectives.
• Mentor engineers and contribute to technical direction, architecture decisions, and engineering standards.

Required Skills

Strong expertise in Python and backend engineering is central to this position. Candidates should also have a solid understanding of distributed systems and experience designing scalable software architectures.

Deep hands-on experience with Agentic AI, LLM applications, LangGraph, and RAG architectures is required. Candidates should understand how AI agents and LLM-powered applications are designed, deployed, monitored, and improved in production.

Experience operationalizing deep learning and LLM models is important, including practical knowledge of production deployment, safeguards, rollback approaches, prompt versioning, and performance optimization.

The role also requires experience optimizing LLM workloads across token consumption, latency, throughput, and cost. Familiarity with LLM evaluation and observability platforms such as LangSmith or equivalent tools is expected.

Strong ETL optimization knowledge is required, including workload-aware scheduling, partition pruning, caching, and storage-format tuning. Candidates should also be comfortable working with APIs, databases, distributed systems, and cloud platforms.

Preferred Skills

Candidates who have experience leading large cross-functional initiatives and mentoring engineers will be well suited to the role. The ability to convert complex business and technical requirements into scalable engineering solutions is valuable.

Experience with AWS cloud-native services, Docker, Kubernetes, and enterprise platform integration patterns is preferred. Knowledge of network technologies can also be useful when designing distributed AI platforms.

Experience integrating Model Context Protocol and related AI tool ecosystems is an additional advantage. Strong technical communication skills are important, particularly the ability to explain architecture and complex AI engineering topics clearly to stakeholders and technical leadership.

Education

The provided job description does not specify a required degree or educational qualification. Candidates should therefore be assessed against the stated hands-on experience, technical capabilities, and professional expertise.

Experience

The job description states a minimum range of 5 to 10 years of hands-on experience across machine learning engineering, backend development, and applied AI. The original job title references 5 to 8 years, while the minimum qualifications section states 5 to 10 years. Candidates should review the employer's application page for the current eligibility interpretation.

The position is intended for experienced engineers with substantial practical exposure to Agentic AI, LLM applications, Python backend development, distributed systems, RAG architectures, and production AI workloads.

Required Technologies

Core technologies and platforms include Python, LangGraph, LLMs, Agentic AI, RAG, deep learning, AWS, Amazon S3, Amazon SQS, Amazon SNS, AWS Lambda, Docker, Kubernetes, APIs, databases, distributed systems, ETL, LangSmith or equivalent LLM observability tools, and Model Context Protocol.

Relevant engineering areas include cloud-native architecture, multi-agent systems, prompt versioning, runtime safeguards, rollback strategies, LLM evaluation, token optimization, latency optimization, throughput optimization, cost optimization, caching, partition pruning, and storage-format tuning.

Soft Skills

The role requires strong technical communication, strategic thinking, and collaboration. Candidates should be able to work with engineering teams, product stakeholders, and other business groups to align technical direction with organizational objectives.

Mentoring ability is important because the position involves influencing engineering standards and helping other engineers grow. Strong problem-solving skills, ownership, structured decision-making, and the ability to communicate complex AI architecture in a clear manner are also important.

Benefits of Working in this Role

This role provides an opportunity to work on advanced Agentic AI and LLM engineering problems while combining software development with cloud, data, and machine learning technologies. The position offers exposure to production AI systems, RAG architectures, multi-agent workloads, cloud-native infrastructure, and AI observability.

The engineering scope also allows experienced professionals to contribute to architecture decisions, technical standards, production reliability, and cross-functional initiatives.

Work Mode

The job is listed as Hybrid. Candidates should be prepared to follow the applicable hybrid working expectations for the Bangalore team.

Location

This Software Engineer position is based in Bangalore, India.

Who Should Apply

This opportunity is suitable for experienced Machine Learning Engineers, AI Engineers, Applied AI Engineers, Backend Engineers, LLM Engineers, and Software Engineers who have strong hands-on experience with production AI systems.

Candidates should be particularly comfortable with Python, Agentic AI, LLM applications, LangGraph, RAG, distributed systems, cloud-native development, and AWS. Professionals with experience in LLM evaluation, observability, ETL optimization, Docker, Kubernetes, and Model Context Protocol can bring additional value.

Career Growth

Experience in this role can support progression toward Staff AI Engineer, Principal AI Engineer, Machine Learning Architect, LLM Architect, AI Platform Architect, or technical leadership positions. Working across AI architecture, backend systems, cloud infrastructure, and production operations can help build broad expertise in enterprise AI engineering.

Application Advice

Before applying, make sure your resume clearly highlights hands-on experience with Agentic AI, LLM applications, LangGraph, RAG, Python, and production AI deployments. Explain the scale and impact of systems you have built or operated where possible.

Include examples of LLM performance optimization, prompt versioning, safeguards, rollback strategies, evaluation, observability, ETL optimization, distributed systems, and AWS architecture. Mention Docker, Kubernetes, LangSmith or equivalent tools, Model Context Protocol, and multi-agent systems when you have practical experience with them.

Also highlight mentoring, architecture ownership, cross-functional leadership, and examples where you translated complex requirements into scalable technical solutions.