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

Overview

Automation Engineer on the AIDCG initiative (Submission Data and Content Generation & Reuse) in Pharma R&D, building production-grade GenAI agents that automate complex, multi-step document generation workflows.

What you'll do

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

What you'll need

• 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.
• 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 and infrastructure: vLLM, Hugging Face TGI, and Ollama (for local development).
• Guardrails and validation: NeMo Guardrails, Guardrails AI, Pydantic, and Instructor.
• LLM ops and observability: Ragas, DeepEval, Langfuse, LangSmith, and Phoenix.
• Data parsing: Unstructured, Apache Tika, LlamaParse, and PDFPlumber.
• Programming and 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 baseline experience: Amazon Bedrock (foundation model access, custom configurations, managed agent workflows), Amazon SageMaker (fine-tuning, hosting, evaluating, and deploying open-source LLMs), Amazon OpenSearch Service (vector search, hybrid search, enterprise retrieval infrastructure), and AWS Step Functions (multi-step orchestration and state machine management for hybrid AI/traditional pipelines).
• 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.

Nice to have

• Clinical document automation, specifically translating protocols to Clinical Study Reports (Protocol → CSR).
• Data lineage workflows: 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.
• Regulatory submissions: familiarity with ICH M11 (protocol/SoA), ICH E3 (CSR), and eCTD Module 5.
• Compliance frameworks: designing software to align strictly with GxP, 21 CFR Part 11, and ICH guidelines, ensuring total auditability, traceability, and explainability.

Details

• Location: Hyderabad.
• Shift: CET time zone.