Principal Engineer

Role overview

This position is for an AI Systems Architect/Principal Engineer responsible for shaping and delivering production-ready agentic and Generative AI solutions. The role is highly technical and hands-on, with accountability for architecture, implementation guidance, performance tuning, stability, observability, and release readiness.

About the company

The organization is a global technology services and consulting firm focused on helping clients solve complex digital transformation challenges. It combines consulting, design, engineering, and operations capabilities to build sustainable, future-ready businesses and serves clients across many countries. The company also states that it is an equal opportunity employer and makes hiring decisions without discrimination based on protected characteristics.

Core responsibilities

The role centers on designing secure, scalable, and cost-conscious AI platforms on AWS while supporting delivery teams through debugging, optimization, and engineering standards.

• Design end-to-end architectures for agentic systems, GenAI/RAG pipelines, and evaluation workflows, including detailed design documentation with flow diagrams, UML, sequence diagrams, and AWS deployment topologies.
• Plan for advanced LLM training and inference patterns, including distributed approaches that improve scalability.
• Analyze and optimize throughput, latency, concurrency, autoscaling, CPU/GPU sizing, and vector index performance for efficient deployments.
• Support multi-node GPU clusters and distributed training efficiency to reduce compute overhead.
• Lead deep debugging efforts, resolve critical defects, and handle production incidents with a focus on stability and performance.
• Pair with developers to improve code quality, while applying configuration management and automated recovery practices for high availability.
• Create reference implementations using Semantic Kernel, LangGraph, AutoGen, or CrewAI, with emphasis on schema validation, grounding, and memory handling.
• Implement distributed tracing, logging, and metrics using OpenTelemetry and Datadog, and define dashboards, alerts, and incident workflows.
• Build evaluation and rollout mechanisms such as golden datasets, A/B testing, regression suites, and controlled deployments.
• Develop reusable SDKs, connectors, CI/CD templates, and architecture review checklists to standardize engineering practices.
• Work with product, data, and SRE teams on capacity planning, disaster recovery strategies, and post-incident root cause analysis.
• Mentor engineers to improve solution design, reliability, and delivery quality.

Requirements

• Bachelor’s or Master’s degree from a top-tier institute such as IIT/Tier-1, preferably in Computer Science, AI, or a related discipline.
• 7 to 10 years of experience in software or AI engineering.
• At least 4 years of hands-on work in GenAI application development.
• At least 2 years of experience designing agentic AI systems.
• Strong proficiency in Python 3.11 or newer, including asyncio, typing, packaging, profiling, and pytest.
• Practical experience with Semantic Kernel, LangGraph, AutoGen, or CrewAI.
• Delivered GenAI/RAG solutions on AWS Bedrock or comparable vector-based platforms such as OpenSearch Serverless, Pinecone, or Redis.
• Strong knowledge of the AWS ecosystem, including EKS, Bedrock, S3, SQS/SNS, RDS, ElastiCache, Secrets Manager, IAM/Okta, and Kong API Gateway.

Eligibility

Any graduate can apply, though the role description also emphasizes preference for candidates with advanced technical education from top-tier institutions.

Important note

The company warns applicants to be cautious of fraudulent job offers requesting cash deposits or any payment for employment. It clearly states that it does not ask candidates for money at any stage of the hiring process.

Additional context

The role is based in Bengaluru, India, and the position calls for an experienced professional who can combine architecture ownership with deep hands-on engineering. The listed mandatory skill focus is GenAI for Internet Software Products, and the experience expectation is 8 to 10 years.