Software Engineer II A - GBS IND

Responsibilities: -

GenAI Development & Implementation

• Design and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines including document processing, embedding generation, vector storage, and retrieval optimization
• Build and deploy LLM-based applications using frameworks like LangChain, LlamaIndex, or Haystack
• Develop prompt engineering workflows, template libraries, and prompt optimization strategies for enterprise use cases
• Implement fine-tuning pipelines using LoRA, QLoRA, Adapters, or instruction tuning methodologies
• Build agent-based architectures with tool augmentation and multi-step reasoning capabilities
• Integrate multimodal models handling text, tabular data, and unstructured content

Platform & Infrastructure

• Develop production-grade model serving infrastructure using Docker, Kubernetes/OpenShift, and model frameworks
• Build scalable inference APIs with load balancing, caching, and request routing
• Implement vector database solutions with optimized indexing and search
• Design and deploy microservices for data preprocessing, feature extraction, and post-processing
• Optimize model inference performance through quantization, batching, and hardware acceleration

MLOps & Model Lifecycle

• Build CI/CD pipelines for model deployment, versioning, and rollback
• Implement model monitoring, drift detection, and automated evaluation frameworks
• Develop A/B testing infrastructure for model comparison and champion/challenger strategies
• Create logging and observability solutions for LLM requests, responses, and performance metrics
• Build hallucination detection, factuality checks, and safety guardrails into production pipelines

Collaboration & Delivery

• Partner with business stakeholders, quants, and product managers to translate requirements into technical solutions
• Conduct code reviews and provide technical mentorship to junior engineers
• Participate in architecture discussions and contribute to platform design decisions
• Drive agile delivery with sprint planning, estimation, and on-time execution
• Document technical designs, APIs, and operational runbooks

Innovation & Quality

• Research and prototype emerging GenAI technologies and techniques
• Conduct performance benchmarking and optimization of AI workloads
• Implement comprehensive testing strategies including unit, integration, and evaluation tests
• Address security, compliance, and data privacy requirements across AI workflows
  • Stay current with advances in LLMs, embeddings, vector search, and AI infrastructure