17 hours ago
Hyderābād, IndiaSenior
Responsibilities
- Design and build LLM application components such as prompts, tools, agents, orchestration flows, memory and context handling, retrieval pipelines, and evaluation harnesses.
- Build data-grounded agentic applications on the Databricks lakehouse using RAG, Delta tables, Vector Search, governed features, MLflow, Model Serving, and Unity Catalog.
- Implement ingestion, parsing, chunking, enrichment, embeddings, vector search, and retrieval workflows for structured and unstructured enterprise content.
- Engineer safety and control components including PII detection and redaction, prompt-injection defenses, content filters, guardrails, authentication, authorization, lineage, and audit logging.
- Collaborate with architects, data engineers, product owners, and security stakeholders to deliver tested, observable, maintainable software components.
- Maintain component designs, integration specifications, deployment runbooks, evaluation results, and reusable engineering patterns.
- Contribute code, architecture decisions, technical documentation, and reusable engineering patterns as a hands-on technical or engineering lead.
Requirements
- Bachelor's degree in Computer Science, Computer Engineering, Data Science, AI/ML, Information Technology, or a related engineering discipline, with 15 years of full-time education.
- At least 5 years of software, data, or AI engineering experience, including 2 years of cloud-native engineering and 1 year of GenAI, LLM, NLP, or agentic AI delivery; alternatively, 7+ years with 3+ years in cloud-native architecture or engineering and 1–2+ years in GenAI, LLM, NLP, or agentic AI delivery.
- Hands-on Python coding experience and strong understanding of APIs, distributed systems, testing, observability, and secure SDLC practices.
- Experience with Databricks Mosaic AI, Model Serving, Agent Framework, MLflow tracing and evaluation, Vector Search, Unity Catalog, Delta Lake, Lakehouse Monitoring, Feature Store, Databricks Workflows, Jobs, notebooks, and Model Training.
- Understanding of LLM application architecture, including RAG, function and tool calling, agent orchestration, model invocation, prompt engineering, embeddings, vector databases, and evaluation metrics.
- Ability to implement traditional ML and GenAI components across ingestion, data and feature preparation, model integration, deployment, monitoring, and continuous improvement.
- Experience delivering AI, ML, or data products in an industry such as financial services, healthcare, manufacturing, retail, telecom, or life sciences.
- Knowledge of security, privacy, governance, performance, scalability, reliability, and cost controls for production AI systems.
- Experience with Git-based development, automated testing, CI/CD pipelines, infrastructure-as-code, and agile delivery in client-facing environments.
- Preferred experience includes Databricks certifications, Spark or PySpark, Delta Live Tables, LangGraph, LangChain, model fine-tuning, lakehouse optimization, LlamaIndex, Haystack, MLflow, FastAPI, Docker, Kubernetes, Responsible AI, model risk management, synthetic data, human-in-the-loop review, A/B testing, and GenAI cost optimization.
Tech Stack
Categories
About Accenture
Accenture is a global professional services firm providing management consulting, systems integration and technology, cybersecurity, and business process outsourcing for enterprises and governments. It operates a services-driven model delivering projects and managed services, often with major cloud and software partners, across industries worldwide. Headquartered in Dublin and publicly traded on the NYSE (ACN), it originated as Andersen Consulting and adopted the Accenture name in 2001.