Full-time
Lead AI/ML Engineer – NLP & Generative AI
Bangalore, India
7+ years
About The Role
We are seeking a Lead AI/ML Engineer with deep expertise in Natural Language Processing (NLP) and Generative AI to lead the design and development of advanced AI-driven solutions in the Electrification domain. You will be part of our cutting-edge AI Solutions team, guiding the architecture and implementation of production-grade LLM and Agentic AI applications.
Key Responsibilities
Core Responsibilities
- Architect and lead the development of NLP and Generative AI solutions, including LLM integration, RAG pipelines, and multi-agent frameworks
- Design and optimize retrieval systems using knowledge graphs and vector databases, improving contextual accuracy and semantic relevance in RAG workflows
- Apply advanced techniques (e.g., document chunking strategies, re-rankers, hybrid retrieval, query rewriting, feedback loops) to enhance RAG chain precision and reduce hallucinations
- Collaborate with ontology/domain experts to integrate structured knowledge bases and semantic relationships into the solution stack
- Leverage modern frameworks like LangGraph, LangChain, LlamaIndex, Smol Agents, and others for orchestrating agent-based and tool-augmented pipelines
- Incorporate AWS Bedrock, SageMaker, Azure ML Studio, Azure OpenAI Service, and Azure AI Foundry for cloud-native scalability and operational efficiency
- Ensure high observability and maintainability of AI solutions through robust MLOps practices, logging, and model monitoring
- Lead code/design reviews, mentor team members, and help shape long-term AI strategy and technical roadmaps
- Collaborate with product, cloud, software, and data engineering teams to deploy impactful AI capabilities in real-world settings
Qualifications
Education: Bachelor's or Master's degree in Computer Science, Machine Learning, AI, or a related field
Experience: 7+ years of AI/ML experience, with 3–4 years in NLP, and 2+ years in Generative AI applications
Required Skills
- Expertise in designing production-grade RAG systems, including single-agent and multi-agent architectures
- Solid understanding of LLM internals, prompt engineering, fine-tuning (LoRA, PEFT), and use of open-source and hosted foundation models
- Experience with Knowledge Graphs, graph databases (e.g., Neo4j), and semantic enrichment strategies
- Proficiency in Python and hands-on experience with frameworks like LangGraph, LlamaIndex, Transformers, and SmolAgents
- Knowledge of vector databases (e.g., Azure AI Search, FAISS, Weaviate, Pinecone) and search optimization techniques
- Familiarity with model observability tools, evaluation frameworks, and performance diagnostics
- Strong experience with AWS and/or Azure managed services for AI development
Preferred Skills
- Experience incorporating ontologies, taxonomies, and domain-specific schemas in knowledge-enhanced AI systems
- Prior exposure to industrial AI or Electrification/Power sector challenges is a strong plus
- Knowledge of hybrid retrieval techniques combining symbolic and statistical methods
- Strong stakeholder engagement and mentoring capabilities
- Familiarity with compliance, safety, and ethical considerations in LLM deployments
Submit Your Application
Fill out the form below and we'll get back to you shortly.
Full Name *
Email Address *
Phone Number *
Attach Resume * (PDF or Word, Max 5MB)
Click to upload your resume
By applying, you agree to our terms and privacy policy
Why Isarva Infotech
Work-Life Balance
Flexible hours and remote options
Growth Opportunities
Continuous learning and development
Great Team
Collaborative and supportive environment
Competitive Package
Industry-leading compensation
Know someone perfect for this role Share this opportunity with them!
Excited about this opportunity
Apply using the form above, or explore more career opportunities with Isarva Infotech.
View All Openings Learn About culture
