1 month ago
Bengaluru, IndiaStaff+
Responsibilities
- Architect production-grade agentic systems, GenAI/RAG pipelines, evaluation workflows, and AWS deployment topologies.
- Design and optimize throughput, latency, concurrency, autoscaling, CPU/GPU sizing, vector indexes, multi-node GPU clusters, and distributed training.
- Debug critical defects, resolve production incidents, pair-program with developers, and improve system stability and code quality.
- Build reference implementations using Semantic Kernel, LangGraph, AutoGen, or CrewAI with schema validation, grounding, and memory management.
- Implement distributed tracing, metrics, logging, dashboards, alerts, and incident response workflows using OpenTelemetry and Datadog.
- Develop evaluation frameworks covering golden sets, A/B experiments, regression suites, and controlled rollouts.
- Create reusable SDKs, connectors, CI/CD templates, and architecture review checklists.
- Collaborate with product, data, and SRE teams on capacity planning, disaster recovery, and post-incident reviews.
- Mentor engineers and establish technical, design, reliability, and production-readiness standards.
Requirements
- Bachelor’s or master’s degree from a top-tier institute in Computer Science, AI, or a related field.
- 5–8 years of experience in GenAI for internet software products; the qualifications section also specifies 7–10 years of software or AI engineering experience.
- At least 4 years of GenAI application development experience and 2 years architecting agentic AI systems.
- Expertise in Python 3.11+, including asyncio, typing, packaging, profiling, and pytest.
- Hands-on experience with Semantic Kernel, LangGraph, AutoGen, CrewAI, or equivalent frameworks.
- Experience delivering GenAI/RAG systems using AWS Bedrock or equivalent vector-based platforms such as OpenSearch Serverless, Pinecone, or Redis.
- Deep understanding of AWS services and ecosystem components including EKS, Bedrock, S3, SQS/SNS, RDS, ElastiCache, Secrets Manager, IAM/Okta, and Kong API Gateway.
- Experience with advanced LLM training and inference workflows, distributed strategies, GPU clusters, model adaptation, compression, and optimization.
Categories
About Wipro
Wipro is a global IT services and consulting firm that provides application development, cloud migration, infrastructure management, data/AI, and business process outsourcing for enterprises. It earns revenue through long-term outsourcing, managed services, and project-based consulting across multiple industries. Founded in 1945 and headquartered in Bangalore, India, Wipro is publicly traded (NYSE: WIT; NSE/BSE: WIPRO).