Project Role: Large Language Model ArchitectProject Role Description

Architect large language models (LLM) that can process and generate natural language. Design neural network parameters, trained on large quantities of unlabeled text data.

Must Have Skills

- Large Language Models (LLMs)

Good to Have Skills

- Databricks Unified Data Analytics Platform

Experience Required

- Minimum 7.5 year(s) of experience is required

Educational Qualification

- 15 years full-time education

Role Summary / Description

AI Powered Tech Talent

Engineer role in AI LLM Technology Architecture. Hands-on engineering role focused on designing, building, integrating, testing, and operationalizing enterprise-grade LLM, GenAI, and agentic AI components across active client engagements. Own platform-specific engineering on Databricks, translating high-level architecture into working, production-quality components for LLM-driven applications, RAG pipelines, multi-agent workflows, and AI platform integrations. Bring practical industry experience in financial services, healthcare, manufacturing, retail, telecom, or life sciences to identify domain data, process constraints, controls, and adoption risks while designing GenAI solutions that are safe, scalable, and relevant. Operate as a hands-on technical lead or engineering lead, contributing code, design decisions, reusable patterns, and engineering documentation.

Key Responsibilities

- Design and build LLM application components including prompts, tools, agents, orchestration flows, memory/context handling, retrieval pipelines, and evaluation harnesses.
- Build data-grounded agentic applications on the lakehouse implement RAG with Delta tables, Vector Search,



and governed features use MLflow for tracing, evaluation, and model lifecycle deploy agents or models with Model Serving and enforce governance through Unity Catalog.
- Implement data ingestion, parsing, chunking, enrichment, embeddings, vector search, and retrieval workflows for structured and unstructured enterprise content.
- Engineer safety and control components including PII detection/redaction, prompt-injection defenses, content filters, guardrails, authentication, authorization, lineage, and audit logging.
- Collaborate with architects, data engineers, product owners, and security stakeholders to convert solution designs into tested, observable, and maintainable software components.
- Maintain technical artifacts such as component designs, integration specifications, deployment runbooks, evaluation results, and reusable engineering patterns.

Required Qualifications

- Bachelor's degree in Computer Science, Computer Engineering, Data Science, AI/ML, Information Technology, or a related engineering discipline.
- Hands-on coding experience in Python and strong understanding of APIs, distributed systems, CI/CD, testing, observability, and secure SDLC practices.
- Experience delivering AI/ML or data products in at least one industry domain such as financial services, healthcare, manufacturing, retail,



telecom or life sciences.

Required Skills/Experience

- Hands-on experience with Databricks Mosaic AI, Model Serving, Agent Framework, MLflow tracing/evaluation, Vector Search, Unity Catalog, Delta Lake, Lakehouse Monitoring, Feature Store, Databricks Workflows, Jobs, notebooks and Model Training.
- Robust understanding of LLM application architecture patterns including RAG, function/tool calling, agent orchestration, model invocation, prompt engineering, embeddings, vector databases, and evaluation metrics.
- Ability to implement traditional ML and GenAI components across ingestion, feature/data preparation, model integration, deployment, monitoring, and continuous improvement.
- Practical 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.

Good to Have Skills

- Databricks Machine Learning, Data Engineer or Generative AI certification experience with Spark/PySpark, Delta Live Tables, Unity Catalog governance, LangGraph/LangChain, model fine-tuning, and lakehouse cost/performance optimization.
- Exposure to open-source frameworks such as LangChain, LangGraph, LlamaIndex, Haystack, MLflow, FastAPI, Docker, and Kubernetes.
- Experience with Responsible AI, model risk management, synthetic data generation, human-in-the-loop review, A/B testing, and GenAI cost optimization.

Locations

- Job No. ATCI-5700970-S2061680 | Pune | Required Skill: Large Language Models (LLMs)

📌 Large Language Model Architect (Pune)
🏢 Accenture
📍 Pune