Role Overview:-
We are seeking an accomplished Lead AI Engineer – Agentic AI & LLM Systems to design, develop, and deliver sophisticated, production-ready agentic AI architectures.
In this role, you will take ownership of critical AI engineering components, including multi-agent orchestration, advanced Retrieval-Augmented Generation (RAG) pipelines, intelligent document processing, memory systems, and enterprise AI integrations.
You will work with modern AI frameworks such as LangGraph, LangChain, AutoGen, and CrewAI, integrating leading LLM platforms and cloud technologies to build scalable, secure, observable, and reliable AI solutions.
This is a hands-on technical leadership opportunity for an engineer who has successfully transitioned AI innovations from proof-of-concept to production environments and can drive engineering excellence across complex AI initiatives.
Key Responsibilities:-
1. Agentic AI Architecture & Engineering
- Design, develop, and optimize sophisticated multi-agent systems using LangGraph, LangChain, AutoGen, CrewAI, or equivalent frameworks.
- Build intelligent agent workflows covering orchestration, tool execution, retrieval, reasoning, and memory management.
- Define agent architectures, component boundaries, API contracts, data flows, and failure-handling strategies.
- Develop reusable AI components and scalable agent orchestration patterns.
2. Advanced RAG & Intelligent Information Retrieval
- Architect and optimize production-grade RAG pipelines, including document ingestion, preprocessing, chunking, embeddings, and retrieval strategies.
- Implement vector-based and hybrid search solutions using Pinecone, Weaviate, pgvector, or equivalent technologies.
- Evaluate retrieval accuracy, contextual relevance, and response quality using RAGAS or custom evaluation frameworks.
- Optimize retrieval performance, system latency, and response reliability.
3. LLM Integration & AI Development
- Integrate enterprise LLM services through Anthropic Claude API, OpenAI APIs, Vertex AI Agent Builder, or equivalent platforms.
- Implement advanced tool calling, streaming, structured outputs, and context management.
- Develop intelligent document processing solutions for pharmaceutical and life sciences content.
- Build AI-powered capabilities for clinical research, medical affairs, commercial analytics, and regulatory intelligence.
4. Enterprise Data & Platform Integration
- Integrate AI applications with pharmaceutical data platforms, including IQVIA, Symphony Health, Komodo Health, Veeva, and related ecosystems.
- Develop robust REST API integrations, event-driven workflows, and batch processing pipelines.
- Leverage knowledge graphs and graph databases such as Neo4j and Amazon Neptune where applicable.
- Support data-driven applications for KOL mapping, competitive intelligence, and market intelligence.
5. Production Engineering & Cloud Deployment
- Deploy and manage AI applications across AWS, Azure, or Google Cloud Platform.
- Implement containerized solutions using Docker and Kubernetes.
- Establish infrastructure automation using Terraform, AWS CDK, or equivalent tools.
- Drive CI/CD automation, integration testing, deployment validation, and rollback strategies.
- Ensure production reliability, scalability, and maintainability.
6. AI Observability, Evaluation & Governance
- Establish comprehensive monitoring and observability using LangSmith, Helicone, or equivalent platforms.
- Monitor agent execution traces, token consumption, latency, cost efficiency, and response quality.
- Develop evaluation frameworks, performance benchmarks, drift monitoring, and quality assurance mechanisms.
- Implement secure and auditable AI engineering practices aligned with HIPAA, GxP, and 21 CFR Part 11 requirements.
7. Technical Leadership & Collaboration
- Own end-to-end technical delivery of assigned AI subsystems.
- Conduct architecture reviews, code reviews, and technical design discussions.
- Mentor AI engineers and provide technical guidance on complex implementation challenges.
- Translate business and domain requirements into clear technical specifications.
- Collaborate with cross-functional teams and communicate architectural decisions to technical and non-technical stakeholders.
Pay: ₹2,200,000.00 - ₹3,600,000.00 per year
Application Question(s):
- How many years of total software/ML engineering experience do you have?
- How many years of hands-on experience do you have building production-grade LLM or Agentic AI systems?
- Which Agentic AI frameworks have you used hands-on (LangGraph, LangChain, AutoGen, CrewAI)?
- Have you deployed at least 2 Agentic AI/LLM systems into production?
- Do you have hands-on experience with RAG, vector databases, embeddings, and hybrid search?
- Have you worked with Anthropic Claude API, OpenAI APIs, or Vertex AI Agent Builder?
- Which cloud platforms have you used: AWS, Azure, or GCP? Do you have Docker and Kubernetes experience?
- Please provide your current CTC and expected CTC, including fixed and variable components.
- What is your current notice period and confirmed last working day? Can you join within one week?
- Are you currently based in Bengaluru or willing to work from the Bengaluru office 4 days per week, with up to 6 WFH days per month?
Education:
Experience:
- Agentic AI & LLM Systems to design, develop, and deliver: 6 years (Required)
Work Location: In person
