Automation Engineer Submission Data and Content Generation & Reuse (AIDCG) - Pharma R&D

Roche; Hyderabad; On-site; INR 1,200,000 - 2,200,000; Full time

Job summary

Roche is hiring a GenAI Agent Developer to join the AIDCG initiative. You will design, build, and operate multi-agent systems and advanced RAG pipelines in a secure, scalable AWS environment.

The role emphasizes governance, performance, and compliant outputs across structured data transformations, with strong focus on memory management and guardrails. You'll collaborate with data scientists and engineers to produce production-grade AI agents, maintaining observability and implementing best

Qualifications

• Demonstrated ownership of ambiguous tasks and driving initiatives
• Proven track record speaking at internal technical events
• Ability to collaborate across diversified teams and share knowledge

Responsibilities

• Design, deploy, and scale multi-agent orchestration systems
• Build and optimize RAG pipelines over large datasets
• Implement robust state management and memory systems in agent networks
• Create evaluation metrics, observability pipelines, and guardrails for safety and quality
• Monitor and optimize AI inference cost, latency, and throughput
• Implement access controls, data encryption, and prompt-injection mitigation
• Document reusable agent patterns and components for cross-functional teams

Skills

GenAI Development

LangChain

Prompt engineering

RAG pipelines

Python

Docker

Kubernetes

Security

Cloud AWS

MCP

Education

Masters in CS/AI

Bachelor's in CS/AI

Tools

FAISS

Hugging Face TGI

LangGraph

LlamaIndex

CrewAI

AutoGen

DSPy

Job description

At Roche you can show up as yourself, embraced for the unique qualities you bring. Our culture encourages personal expression, open dialogue, and genuine connections, where you are valued, accepted and respected for who you are, allowing you to thrive both personally and professionally. This is how we aim to prevent, stop and cure diseases and ensure everyone has access to healthcare today and for generations to come. Join Roche, where every voice matters.

The Position

About The Role

We are hiring a GenAI Agent Developer to join the AIDCG initiative, a transformative program focused on automating complex, multi-step document generation workflows through state-of-the-art AI agents.

This role blends advanced GenAI engineering, open-source innovation, and AWS cloud expertise to deliver production-grade AI agents that are accurate, scalable, and highly secure. You will design orchestration frameworks that transform raw, unstructured data into highly structured, compliant outputs.

Description of the area

Job Responsibilities

• Agentic Architecture: Design, deploy, and scale multi-agent orchestration systems and autonomous workflows using cutting-edge frameworks
• Advanced RAG Pipelines: Build and optimize advanced retrieval-augmented generation (RAG) pipelines over massive, heterogeneous datasets (structured and unstructured)
• State & Memory Management: Implement robust state management, short/long-term memory systems, and self-correction/reflection loops within agent networks
• Evaluation & Guardrails: Create and implement robust evaluation metrics, observability pipelines, and guardrails for content quality, hallucination reduction, bias mitigation, and safety standards
• Performance Optimization: Monitor and optimize AI inference cost, latency, throughput, token usage, and overall system reliability
• Security & Access Control: Implement robust access controls, data encryption, user authentication, and prompt injection mitigation across all LLM workflows
• Collaboration & Best Practices: Document and share reusable agent patterns, prompt libraries, and engineering components across cross-functional technical teams

Qualifications

Education / Experience

• Demonstrated experience taking ownership of ambiguous tasks, successfully driving small to medium initiatives, and acting as a technical mentor
• Proven track record of engaging in knowledge-sharing initiatives, speaking at internal technical events, and navigating group dynamics in diversified settings

Technical Skills

• GenAI Development: Advanced prompt engineering, fine-tuning, RAG/GraphRAG, schema-constrained outputs, function/tool-calling, and semantic caching
• Agentic Frameworks: LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, and DSPy
• Vector Databases: FAISS, Milvus, Qdrant, Pinecone, Weaviate, and Pgvector
• LLM Serving & Infra: vLLM, Hugging Face TGI, and Ollama (for local development)
• Guardrails & Validation: NeMo Guardrails, Guardrails AI, Pydantic, and Instructor
• LLM Ops & Observability: Ragas, DeepEval, Langfuse, LangSmith, and Phoenix
• Data Parsing: Unstructured, Apache Tika, LlamaParse, and PDFPlumber
• Programming & DevOps: Python (FastAPI, asyncio), REST/GraphQL APIs, Git, CI/CD pipelines, Docker, Kubernetes, and OpenTelemetry
• Emerging Protocols: Model Context Protocol (MCP) and Agent2Agent communication standards

AWS Ecosystem (Baseline Experience)

• Amazon Bedrock: Foundation model access, custom configurations, and managed agent workflows
• Amazon SageMaker: Fine-tuning, hosting, evaluating, and deploying open-source LLMs
• Amazon OpenSearch Service: Vector search, hybrid search, and enterprise retrieval infrastructure
• AWS Step Functions: Multi-step orchestration and state machine management for hybrid AI/traditional pipelines

Additional Qualifications

• Problem-Solving: An analytical mindset capable of breaking down highly abstract, ambiguous logic loops into predictable agent behaviors
• Collaboration: Ability to thrive in a fast-paced, product-focused agile engineering environment alongside data scientists and product owners
• Communication: Strong technical writing and communication skills for documenting complex system architectures and cross-functional collaboration

Bonus: Domain & Regulatory Knowledge

Experience or strong familiarity with the following clinical trial standards will give you a significant advantage:

• Clinical Document Automation: Automating the full clinical document generation workflow, specifically translating protocols to Clinical Study Reports (Protocol CSR)
• Data Lineage Workflows: Experience transforming raw clinical data and statistical outputs into structured regulatory documents (SDTM/ADaM/ARD TLG CSR)
• CDISC Standards: Deep understanding of CDASH (CRFs), SDTM, ADaM, ARD/ARM, and Define-XML
• Compliance Frameworks: Designing software to align strictly with GxP, 21 CFR Part 11, and ICH guidelines, ensuring total auditability, traceability, and explainability

Shift: CET time zone

#hyderabad2026

Who we are

A healthier future drives us to innovate. Together, more than 100’000 employees across the globe are dedicated to advance science, ensuring everyone has access to healthcare today and for generations to come. Our efforts result in more than 26 million people treated with our medicines and over 30 billion tests conducted using our Diagnostics products. We empower each other to explore new possibilities, foster creativity, and keep our ambitions high, so we can deliver life-changing healthcare solutions that make a global impact.

Let’s build a healthier future, together.

Roche is an Equal Opportunity Employer.