Senior AI Developer (Generative AI / LLM Systems)

Location : Bangalore (Hybrid - 5 days working, 3 days work from office)

Experience : 6-10 years (with strong hands-on experience building GenAI / LLM systems)

Role Type : Individual Contributor

Reporting to : Engineering Manager/Director

Role Overview :

We are seeking a Senior AI Developer (GenAI specialization) to design, build, and operate production-grade Generative AI systems that enable natural-language interaction over large-scale enterprise document ecosystems.

This is a builder and systems-engineering role, not a research or analytics position. You will work from first principles to engineer robust, scalable, and observable GenAI platforms, owning critical components across the lifecycle-from document ingestion and retrieval to LLM orchestration, API serving, and cloud deployment.

You will collaborate closely with senior engineers and architects while taking clear ownership of execution-level design and delivery for core GenAI systems.

Key Responsibilities :

GenAI Systems & Application Development :

- Design and build enterprise-grade GenAI applications (chatbots, copilots, assistants) that support natural-language search across large document repositories and structured data.

- Develop end-to-end RAG pipelines, including document ingestion, intelligent chunking, metadata extraction, indexing, retrieval, and response generation.

- Implement agentic and tool-using AI workflows for complex reasoning, orchestration, and large-scale document interaction.

Retrieval & Knowledge Engineering :

- Build and optimize vector database pipelines for semantic search, context management, chat memory, and source attribution.

- Implement advanced retrieval strategies, including :

1. Hybrid search (semantic + keyword)

2. Multi-stage retrieval and re-ranking

3. Relevance scoring and evaluation techniques

- Debug and improve retrieval quality, grounding accuracy, and hallucination mitigation in production systems.

LLM Integration & Optimization :

- Integrate and optimize LLMs via AWS Bedrock or Azure OpenAI, including :

1. Context window and token optimization

2. Streaming responses

3. Citation and traceability mechanisms

- Apply LLM optimization techniques (prompt design, fine-tuning where applicable, and model compression) to balance response quality, latency, and cost.

Backend, APIs & Cloud Deployment :

- Build production-ready REST APIs using FastAPI (or similar frameworks), with proper error handling, authentication, and concurrency support.

- Deploy and scale GenAI services on AWS, handling high-throughput, concurrent user traffic.

- Identify and resolve performance bottlenecks, latency issues, and infrastructure cost inefficiencies.

Quality, Monitoring & Governance :

- Implement evaluation metrics and monitoring for GenAI/RAG systems (retrieval quality, latency, failure modes).

- Apply best practices around AI safety, ethics, governance, and observability in production environments.

- Contribute to internal documentation, reusable components, and GenAI engineering standards.

- Support mentoring and knowledge-sharing to help evolve the organization's GenAI engineering culture.

Required Skills & Experience :

Core Technical Skills (Must-Have) :

- Strong hands-on experience building GenAI / LLM applications from scratch, beyond simple API consumption or demos.

- Deep practical expertise in :

1. Document chunking strategies

2. Metadata extraction

3. Multi-format document pipelines (PDF, DOC, HTML, etc.)

4. Context and memory management for conversational systems

5. Vector databases in production: indexing, retrieval optimization, and performance tuning.

- Embeddings and semantic search: sentence transformers, similarity search, distance metrics.

- Advanced RAG techniques: hybrid retrieval, re-ranking, and multi-step retrieval.

- Backend engineering experience with RESTful APIs (FastAPI or equivalent).

- Cloud-native development and deployment on AWS.

LLM & Platform Skills :

- Production LLM integration using AWS Bedrock, Azure OpenAI, or similar platforms.

- Token efficiency, streaming responses, and response grounding.

- Experience with evaluation frameworks for RAG systems and conversational AI.

- Solid understanding of monitoring, reliability, and cost optimization for AI systems.

Candidates are expected to have deep hands-on ownership in core GenAI systems, with strong working exposure across adjacent areas such as agentic workflows, evaluation, and optimization.

Good to Have :

- Experience with agentic frameworks and tool orchestration.

- Exposure to model fine-tuning, distillation, or compression techniques.

- Familiarity with AI observability tools and governance frameworks.

- Experience supporting enterprise security, compliance, and data privacy requirements.

Why Join Us :

- Build real, production-grade GenAI systems used at enterprise scale.

- High ownership with deep technical impact.

- Opportunity to help shape GenAI engineering standards and best practices.

- Work at the intersection of AI, backend systems, and cloud engineering in a product-driven environment.